Compare commits

..

1 Commits

Author SHA1 Message Date
Folke Behrens
0896dcf3d4 proxy: Add temporary stream_events tool
neondatabase/cloud#19600
2024-11-14 11:49:07 +01:00
775 changed files with 18881 additions and 72037 deletions

View File

@@ -3,16 +3,6 @@
# by the RUSTDOCFLAGS env var in CI.
rustdocflags = ["-Arustdoc::private_intra_doc_links"]
# Enable frame pointers. This may have a minor performance overhead, but makes it easier and more
# efficient to obtain stack traces (and thus CPU/heap profiles). It may also avoid seg faults that
# we've seen with libunwind-based profiling. See also:
#
# * <https://www.brendangregg.com/blog/2024-03-17/the-return-of-the-frame-pointers.html>
# * <https://github.com/rust-lang/rust/pull/122646>
#
# NB: the RUSTFLAGS envvar will replace this. Make sure to update e.g. Dockerfile as well.
rustflags = ["-Cforce-frame-pointers=yes"]
[alias]
build_testing = ["build", "--features", "testing"]
neon = ["run", "--bin", "neon_local"]

View File

@@ -46,9 +46,6 @@ workspace-members = [
"utils",
"wal_craft",
"walproposer",
"postgres-protocol2",
"postgres-types2",
"tokio-postgres2",
]
# Write out exact versions rather than a semver range. (Defaults to false.)

View File

@@ -24,4 +24,3 @@
!storage_controller/
!vendor/postgres-*/
!workspace_hack/
!build_tools/patches

View File

@@ -3,7 +3,6 @@ name: Bug Template
about: Used for describing bugs
title: ''
labels: t/bug
type: Bug
assignees: ''
---

View File

@@ -4,7 +4,6 @@ about: A set of related tasks contributing towards specific outcome, comprising
more than 1 week of work.
title: 'Epic: '
labels: t/Epic
type: Epic
assignees: ''
---

View File

@@ -4,7 +4,6 @@ self-hosted-runner:
- large
- large-arm64
- small
- small-metal
- small-arm64
- us-east-2
config-variables:
@@ -22,9 +21,3 @@ config-variables:
- SLACK_UPCOMING_RELEASE_CHANNEL_ID
- DEV_AWS_OIDC_ROLE_ARN
- BENCHMARK_INGEST_TARGET_PROJECTID
- PGREGRESS_PG16_PROJECT_ID
- PGREGRESS_PG17_PROJECT_ID
- SLACK_ON_CALL_QA_STAGING_STREAM
- DEV_AWS_OIDC_ROLE_MANAGE_BENCHMARK_EC2_VMS_ARN
- SLACK_ON_CALL_STORAGE_STAGING_STREAM
- SLACK_CICD_CHANNEL_ID

View File

@@ -7,9 +7,6 @@ inputs:
type: boolean
required: false
default: false
aws-oicd-role-arn:
description: 'OIDC role arn to interract with S3'
required: true
outputs:
base-url:
@@ -42,8 +39,7 @@ runs:
PR_NUMBER=$(jq --raw-output .pull_request.number "$GITHUB_EVENT_PATH" || true)
if [ "${PR_NUMBER}" != "null" ]; then
BRANCH_OR_PR=pr-${PR_NUMBER}
elif [ "${GITHUB_REF_NAME}" = "main" ] || [ "${GITHUB_REF_NAME}" = "release" ] || \
[ "${GITHUB_REF_NAME}" = "release-proxy" ] || [ "${GITHUB_REF_NAME}" = "release-compute" ]; then
elif [ "${GITHUB_REF_NAME}" = "main" ] || [ "${GITHUB_REF_NAME}" = "release" ] || [ "${GITHUB_REF_NAME}" = "release-proxy" ]; then
# Shortcut for special branches
BRANCH_OR_PR=${GITHUB_REF_NAME}
else
@@ -83,13 +79,6 @@ runs:
ALLURE_VERSION: 2.27.0
ALLURE_ZIP_SHA256: b071858fb2fa542c65d8f152c5c40d26267b2dfb74df1f1608a589ecca38e777
- uses: aws-actions/configure-aws-credentials@v4
if: ${{ !cancelled() }}
with:
aws-region: eu-central-1
role-to-assume: ${{ inputs.aws-oicd-role-arn }}
role-duration-seconds: 3600 # 1 hour should be more than enough to upload report
# Potentially we could have several running build for the same key (for example, for the main branch), so we use improvised lock for this
- name: Acquire lock
shell: bash -euxo pipefail {0}

View File

@@ -8,9 +8,6 @@ inputs:
unique-key:
description: 'string to distinguish different results in the same run'
required: true
aws-oicd-role-arn:
description: 'OIDC role arn to interract with S3'
required: true
runs:
using: "composite"
@@ -22,8 +19,7 @@ runs:
PR_NUMBER=$(jq --raw-output .pull_request.number "$GITHUB_EVENT_PATH" || true)
if [ "${PR_NUMBER}" != "null" ]; then
BRANCH_OR_PR=pr-${PR_NUMBER}
elif [ "${GITHUB_REF_NAME}" = "main" ] || [ "${GITHUB_REF_NAME}" = "release" ] || \
[ "${GITHUB_REF_NAME}" = "release-proxy" ] || [ "${GITHUB_REF_NAME}" = "release-compute" ]; then
elif [ "${GITHUB_REF_NAME}" = "main" ] || [ "${GITHUB_REF_NAME}" = "release" ] || [ "${GITHUB_REF_NAME}" = "release-proxy" ]; then
# Shortcut for special branches
BRANCH_OR_PR=${GITHUB_REF_NAME}
else
@@ -35,13 +31,6 @@ runs:
env:
REPORT_DIR: ${{ inputs.report-dir }}
- uses: aws-actions/configure-aws-credentials@v4
if: ${{ !cancelled() }}
with:
aws-region: eu-central-1
role-to-assume: ${{ inputs.aws-oicd-role-arn }}
role-duration-seconds: 3600 # 1 hour should be more than enough to upload report
- name: Upload test results
shell: bash -euxo pipefail {0}
run: |

View File

@@ -15,19 +15,10 @@ inputs:
prefix:
description: "S3 prefix. Default is '${GITHUB_RUN_ID}/${GITHUB_RUN_ATTEMPT}'"
required: false
aws-oicd-role-arn:
description: 'OIDC role arn to interract with S3'
required: true
runs:
using: "composite"
steps:
- uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: eu-central-1
role-to-assume: ${{ inputs.aws-oicd-role-arn }}
role-duration-seconds: 3600
- name: Download artifact
id: download-artifact
shell: bash -euxo pipefail {0}

View File

@@ -17,34 +17,6 @@ inputs:
compute_units:
description: '[Min, Max] compute units'
default: '[1, 1]'
# settings below only needed if you want the project to be sharded from the beginning
shard_split_project:
description: 'by default new projects are not shard-split, specify true to shard-split'
required: false
default: 'false'
admin_api_key:
description: 'Admin API Key needed for shard-splitting. Must be specified if shard_split_project is true'
required: false
shard_count:
description: 'Number of shards to split the project into, only applies if shard_split_project is true'
required: false
default: '8'
stripe_size:
description: 'Stripe size, optional, in 8kiB pages. e.g. set 2048 for 16MB stripes. Default is 128 MiB, only applies if shard_split_project is true'
required: false
default: '32768'
psql_path:
description: 'Path to psql binary - it is caller responsibility to provision the psql binary'
required: false
default: '/tmp/neon/pg_install/v16/bin/psql'
libpq_lib_path:
description: 'Path to directory containing libpq library - it is caller responsibility to provision the libpq library'
required: false
default: '/tmp/neon/pg_install/v16/lib'
project_settings:
description: 'A JSON object with project settings'
required: false
default: '{}'
outputs:
dsn:
@@ -76,7 +48,7 @@ runs:
\"provisioner\": \"k8s-neonvm\",
\"autoscaling_limit_min_cu\": ${MIN_CU},
\"autoscaling_limit_max_cu\": ${MAX_CU},
\"settings\": ${PROJECT_SETTINGS}
\"settings\": { }
}
}")
@@ -91,23 +63,6 @@ runs:
echo "project_id=${project_id}" >> $GITHUB_OUTPUT
echo "Project ${project_id} has been created"
if [ "${SHARD_SPLIT_PROJECT}" = "true" ]; then
# determine tenant ID
TENANT_ID=`${PSQL} ${dsn} -t -A -c "SHOW neon.tenant_id"`
echo "Splitting project ${project_id} with tenant_id ${TENANT_ID} into $((SHARD_COUNT)) shards with stripe size $((STRIPE_SIZE))"
echo "Sending PUT request to https://${API_HOST}/regions/${REGION_ID}/api/v1/admin/storage/proxy/control/v1/tenant/${TENANT_ID}/shard_split"
echo "with body {\"new_shard_count\": $((SHARD_COUNT)), \"new_stripe_size\": $((STRIPE_SIZE))}"
# we need an ADMIN API KEY to invoke storage controller API for shard splitting (bash -u above checks that the variable is set)
curl -X PUT \
"https://${API_HOST}/regions/${REGION_ID}/api/v1/admin/storage/proxy/control/v1/tenant/${TENANT_ID}/shard_split" \
-H "Accept: application/json" -H "Content-Type: application/json" -H "Authorization: Bearer ${ADMIN_API_KEY}" \
-d "{\"new_shard_count\": $SHARD_COUNT, \"new_stripe_size\": $STRIPE_SIZE}"
fi
env:
API_HOST: ${{ inputs.api_host }}
API_KEY: ${{ inputs.api_key }}
@@ -115,10 +70,3 @@ runs:
POSTGRES_VERSION: ${{ inputs.postgres_version }}
MIN_CU: ${{ fromJSON(inputs.compute_units)[0] }}
MAX_CU: ${{ fromJSON(inputs.compute_units)[1] }}
SHARD_SPLIT_PROJECT: ${{ inputs.shard_split_project }}
ADMIN_API_KEY: ${{ inputs.admin_api_key }}
SHARD_COUNT: ${{ inputs.shard_count }}
STRIPE_SIZE: ${{ inputs.stripe_size }}
PSQL: ${{ inputs.psql_path }}
LD_LIBRARY_PATH: ${{ inputs.libpq_lib_path }}
PROJECT_SETTINGS: ${{ inputs.project_settings }}

View File

@@ -36,8 +36,8 @@ inputs:
description: 'Region name for real s3 tests'
required: false
default: ''
rerun_failed:
description: 'Whether to rerun failed tests'
rerun_flaky:
description: 'Whether to rerun flaky tests'
required: false
default: 'false'
pg_version:
@@ -48,9 +48,6 @@ inputs:
description: 'benchmark durations JSON'
required: false
default: '{}'
aws-oicd-role-arn:
description: 'OIDC role arn to interract with S3'
required: true
runs:
using: "composite"
@@ -61,7 +58,6 @@ runs:
with:
name: neon-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build_type }}-artifact
path: /tmp/neon
aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}
- name: Download Neon binaries for the previous release
if: inputs.build_type != 'remote'
@@ -70,7 +66,6 @@ runs:
name: neon-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build_type }}-artifact
path: /tmp/neon-previous
prefix: latest
aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}
- name: Download compatibility snapshot
if: inputs.build_type != 'remote'
@@ -82,7 +77,6 @@ runs:
# The lack of compatibility snapshot (for example, for the new Postgres version)
# shouldn't fail the whole job. Only relevant test should fail.
skip-if-does-not-exist: true
aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}
- name: Checkout
if: inputs.needs_postgres_source == 'true'
@@ -110,7 +104,7 @@ runs:
COMPATIBILITY_SNAPSHOT_DIR: /tmp/compatibility_snapshot_pg${{ inputs.pg_version }}
ALLOW_BACKWARD_COMPATIBILITY_BREAKAGE: contains(github.event.pull_request.labels.*.name, 'backward compatibility breakage')
ALLOW_FORWARD_COMPATIBILITY_BREAKAGE: contains(github.event.pull_request.labels.*.name, 'forward compatibility breakage')
RERUN_FAILED: ${{ inputs.rerun_failed }}
RERUN_FLAKY: ${{ inputs.rerun_flaky }}
PG_VERSION: ${{ inputs.pg_version }}
shell: bash -euxo pipefail {0}
run: |
@@ -121,8 +115,6 @@ runs:
export DEFAULT_PG_VERSION=${PG_VERSION#v}
export LD_LIBRARY_PATH=${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/lib
export BENCHMARK_CONNSTR=${BENCHMARK_CONNSTR:-}
export ASAN_OPTIONS=detect_leaks=0:detect_stack_use_after_return=0:abort_on_error=1:strict_string_checks=1:check_initialization_order=1:strict_init_order=1
export UBSAN_OPTIONS=abort_on_error=1:print_stacktrace=1
if [ "${BUILD_TYPE}" = "remote" ]; then
export REMOTE_ENV=1
@@ -158,8 +150,15 @@ runs:
EXTRA_PARAMS="--out-dir $PERF_REPORT_DIR $EXTRA_PARAMS"
fi
if [ "${RERUN_FAILED}" == "true" ]; then
EXTRA_PARAMS="--reruns 2 $EXTRA_PARAMS"
if [ "${RERUN_FLAKY}" == "true" ]; then
mkdir -p $TEST_OUTPUT
poetry run ./scripts/flaky_tests.py "${TEST_RESULT_CONNSTR}" \
--days 7 \
--output "$TEST_OUTPUT/flaky.json" \
--pg-version "${DEFAULT_PG_VERSION}" \
--build-type "${BUILD_TYPE}"
EXTRA_PARAMS="--flaky-tests-json $TEST_OUTPUT/flaky.json $EXTRA_PARAMS"
fi
# We use pytest-split plugin to run benchmarks in parallel on different CI runners
@@ -222,14 +221,6 @@ runs:
# The lack of compatibility snapshot shouldn't fail the job
# (for example if we didn't run the test for non build-and-test workflow)
skip-if-does-not-exist: true
aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}
- uses: aws-actions/configure-aws-credentials@v4
if: ${{ !cancelled() }}
with:
aws-region: eu-central-1
role-to-assume: ${{ inputs.aws-oicd-role-arn }}
role-duration-seconds: 3600 # 1 hour should be more than enough to upload report
- name: Upload test results
if: ${{ !cancelled() }}
@@ -237,4 +228,3 @@ runs:
with:
report-dir: /tmp/test_output/allure/results
unique-key: ${{ inputs.build_type }}-${{ inputs.pg_version }}
aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}

View File

@@ -14,11 +14,9 @@ runs:
name: coverage-data-artifact
path: /tmp/coverage
skip-if-does-not-exist: true # skip if there's no previous coverage to download
aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}
- name: Upload coverage data
uses: ./.github/actions/upload
with:
name: coverage-data-artifact
path: /tmp/coverage
aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}

View File

@@ -14,10 +14,6 @@ inputs:
prefix:
description: "S3 prefix. Default is '${GITHUB_SHA}/${GITHUB_RUN_ID}/${GITHUB_RUN_ATTEMPT}'"
required: false
aws-oicd-role-arn:
description: "the OIDC role arn for aws auth"
required: false
default: ""
runs:
using: "composite"
@@ -57,13 +53,6 @@ runs:
echo 'SKIPPED=false' >> $GITHUB_OUTPUT
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: eu-central-1
role-to-assume: ${{ inputs.aws-oicd-role-arn }}
role-duration-seconds: 3600
- name: Upload artifact
if: ${{ steps.prepare-artifact.outputs.SKIPPED == 'false' }}
shell: bash -euxo pipefail {0}

View File

@@ -1,13 +0,0 @@
rust_code: ['**/*.rs', '**/Cargo.toml', '**/Cargo.lock']
rust_dependencies: ['**/Cargo.lock']
v14: ['vendor/postgres-v14/**', 'Makefile', 'pgxn/**']
v15: ['vendor/postgres-v15/**', 'Makefile', 'pgxn/**']
v16: ['vendor/postgres-v16/**', 'Makefile', 'pgxn/**']
v17: ['vendor/postgres-v17/**', 'Makefile', 'pgxn/**']
rebuild_neon_extra:
- .github/workflows/neon_extra_builds.yml
rebuild_macos:
- .github/workflows/build-macos.yml

View File

@@ -17,7 +17,7 @@ jobs:
strategy:
fail-fast: false
matrix:
platform: [ aws-rds-postgres, aws-aurora-serverless-v2-postgres, neon, neon_pg17 ]
platform: [ aws-rds-postgres, aws-aurora-serverless-v2-postgres, neon ]
database: [ clickbench, tpch, userexample ]
env:
@@ -41,9 +41,6 @@ jobs:
neon)
CONNSTR=${{ secrets.BENCHMARK_CAPTEST_CONNSTR }}
;;
neon_pg17)
CONNSTR=${{ secrets.BENCHMARK_CAPTEST_CONNSTR_PG17 }}
;;
aws-rds-postgres)
CONNSTR=${{ secrets.BENCHMARK_RDS_POSTGRES_CONNSTR }}
;;
@@ -73,7 +70,6 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
# we create a table that has one row for each database that we want to restore with the status whether the restore is done
- name: Create benchmark_restore_status table if it does not exist

View File

@@ -19,8 +19,8 @@ on:
description: 'debug or release'
required: true
type: string
test-cfg:
description: 'a json object of postgres versions and lfc/sanitizers states to build and run regression tests on'
pg-versions:
description: 'a json array of postgres versions to run regression tests on'
required: true
type: string
@@ -31,13 +31,12 @@ defaults:
env:
RUST_BACKTRACE: 1
COPT: '-Werror'
AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
jobs:
build-neon:
runs-on: ${{ fromJson(format('["self-hosted", "{0}"]', inputs.arch == 'arm64' && 'large-arm64' || 'large')) }}
permissions:
id-token: write # aws-actions/configure-aws-credentials
contents: read
container:
image: ${{ inputs.build-tools-image }}
credentials:
@@ -48,8 +47,6 @@ jobs:
# io_uring will account the memory of the CQ and SQ as locked.
# More details: https://github.com/neondatabase/neon/issues/6373#issuecomment-1905814391
options: --init --shm-size=512mb --ulimit memlock=67108864:67108864
strategy:
matrix: ${{ fromJSON(format('{{"include":{0}}}', inputs.test-cfg)) }}
env:
BUILD_TYPE: ${{ inputs.build-type }}
GIT_VERSION: ${{ github.event.pull_request.head.sha || github.sha }}
@@ -89,7 +86,6 @@ jobs:
- name: Set env variables
env:
ARCH: ${{ inputs.arch }}
SANITIZERS: ${{ matrix.sanitizers }}
run: |
CARGO_FEATURES="--features testing"
if [[ $BUILD_TYPE == "debug" && $ARCH == 'x64' ]]; then
@@ -102,14 +98,8 @@ jobs:
cov_prefix=""
CARGO_FLAGS="--locked --release"
fi
if [[ $SANITIZERS == 'enabled' ]]; then
make_vars="WITH_SANITIZERS=yes"
else
make_vars=""
fi
{
echo "cov_prefix=${cov_prefix}"
echo "make_vars=${make_vars}"
echo "CARGO_FEATURES=${CARGO_FEATURES}"
echo "CARGO_FLAGS=${CARGO_FLAGS}"
echo "CARGO_HOME=${GITHUB_WORKSPACE}/.cargo"
@@ -145,39 +135,37 @@ jobs:
- name: Build postgres v14
if: steps.cache_pg_14.outputs.cache-hit != 'true'
run: mold -run make ${make_vars} postgres-v14 -j$(nproc)
run: mold -run make 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)
run: mold -run make 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)
run: mold -run make 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)
run: mold -run make postgres-v17 -j$(nproc)
- name: Build neon extensions
run: mold -run make ${make_vars} neon-pg-ext -j$(nproc)
run: mold -run make neon-pg-ext -j$(nproc)
- name: Build walproposer-lib
run: mold -run make ${make_vars} walproposer-lib -j$(nproc)
run: mold -run make walproposer-lib -j$(nproc)
- name: Run cargo build
env:
WITH_TESTS: ${{ matrix.sanitizers != 'enabled' && '--tests' || '' }}
run: |
export ASAN_OPTIONS=detect_leaks=0
${cov_prefix} mold -run cargo build $CARGO_FLAGS $CARGO_FEATURES --bins ${WITH_TESTS}
PQ_LIB_DIR=$(pwd)/pg_install/v16/lib
export PQ_LIB_DIR
${cov_prefix} mold -run cargo build $CARGO_FLAGS $CARGO_FEATURES --bins --tests
# Do install *before* running rust tests because they might recompile the
# binaries with different features/flags.
- name: Install rust binaries
env:
ARCH: ${{ inputs.arch }}
SANITIZERS: ${{ matrix.sanitizers }}
run: |
# Install target binaries
mkdir -p /tmp/neon/bin/
@@ -192,7 +180,7 @@ jobs:
done
# Install test executables and write list of all binaries (for code coverage)
if [[ $BUILD_TYPE == "debug" && $ARCH == 'x64' && $SANITIZERS != 'enabled' ]]; then
if [[ $BUILD_TYPE == "debug" && $ARCH == 'x64' ]]; then
# Keep bloated coverage data files away from the rest of the artifact
mkdir -p /tmp/coverage/
@@ -217,18 +205,12 @@ jobs:
done
fi
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 18000 # 5 hours
- name: Run rust tests
if: ${{ matrix.sanitizers != 'enabled' }}
env:
NEXTEST_RETRIES: 3
run: |
PQ_LIB_DIR=$(pwd)/pg_install/v16/lib
export PQ_LIB_DIR
LD_LIBRARY_PATH=$(pwd)/pg_install/v17/lib
export LD_LIBRARY_PATH
@@ -239,13 +221,8 @@ jobs:
${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_FEATURES -E '!package(pageserver)'
# run pageserver tests with different settings
for get_vectored_concurrent_io in sequential sidecar-task; do
for io_engine in std-fs tokio-epoll-uring ; do
NEON_PAGESERVER_UNIT_TEST_GET_VECTORED_CONCURRENT_IO=$get_vectored_concurrent_io \
NEON_PAGESERVER_UNIT_TEST_VIRTUAL_FILE_IOENGINE=$io_engine \
${cov_prefix} \
cargo nextest run $CARGO_FLAGS $CARGO_FEATURES -E 'package(pageserver)'
done
for io_engine in std-fs tokio-epoll-uring ; do
NEON_PAGESERVER_UNIT_TEST_VIRTUAL_FILE_IOENGINE=$io_engine ${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_FEATURES -E 'package(pageserver)'
done
# Run separate tests for real S3
@@ -279,27 +256,6 @@ jobs:
with:
name: neon-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-artifact
path: /tmp/neon
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Check diesel schema
if: inputs.build-type == 'release' && inputs.arch == 'x64'
env:
DATABASE_URL: postgresql://localhost:1235/storage_controller
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
run: |
/tmp/neon/bin/neon_local init
/tmp/neon/bin/neon_local storage_controller start
diesel print-schema > storage_controller/src/schema.rs
if [ -n "$(git diff storage_controller/src/schema.rs)" ]; then
echo >&2 "Uncommitted changes in diesel schema"
git diff .
exit 1
fi
/tmp/neon/bin/neon_local storage_controller stop
# XXX: keep this after the binaries.list is formed, so the coverage can properly work later
- name: Merge and upload coverage data
@@ -309,10 +265,6 @@ jobs:
regress-tests:
# Don't run regression tests on debug arm64 builds
if: inputs.build-type != 'debug' || inputs.arch != 'arm64'
permissions:
id-token: write # aws-actions/configure-aws-credentials
contents: read
statuses: write
needs: [ build-neon ]
runs-on: ${{ fromJson(format('["self-hosted", "{0}"]', inputs.arch == 'arm64' && 'large-arm64' || 'large')) }}
container:
@@ -324,16 +276,16 @@ jobs:
options: --init --shm-size=512mb --ulimit memlock=67108864:67108864
strategy:
fail-fast: false
matrix: ${{ fromJSON(format('{{"include":{0}}}', inputs.test-cfg)) }}
matrix:
pg_version: ${{ fromJson(inputs.pg-versions) }}
steps:
- uses: actions/checkout@v4
with:
submodules: true
- 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: ${{ matrix.sanitizers != 'enabled' && 60 || 180 }}
timeout-minutes: 60
with:
build_type: ${{ inputs.build-type }}
test_selection: regress
@@ -341,17 +293,13 @@ jobs:
run_with_real_s3: true
real_s3_bucket: neon-github-ci-tests
real_s3_region: eu-central-1
rerun_failed: true
rerun_flaky: true
pg_version: ${{ matrix.pg_version }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
TEST_RESULT_CONNSTR: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
CHECK_ONDISK_DATA_COMPATIBILITY: nonempty
BUILD_TAG: ${{ inputs.build-tag }}
PAGESERVER_VIRTUAL_FILE_IO_ENGINE: tokio-epoll-uring
PAGESERVER_GET_VECTORED_CONCURRENT_IO: sidecar-task
USE_LFC: ${{ matrix.lfc_state == 'with-lfc' && 'true' || 'false' }}
SANITIZERS: ${{ matrix.sanitizers }}
# Temporary disable this step until we figure out why it's so flaky
# Ref https://github.com/neondatabase/neon/issues/4540

View File

@@ -1,89 +0,0 @@
name: Check Codestyle Rust
on:
workflow_call:
inputs:
build-tools-image:
description: "build-tools image"
required: true
type: string
archs:
description: "Json array of architectures to run on"
type: string
defaults:
run:
shell: bash -euxo pipefail {0}
# No permission for GITHUB_TOKEN by default; the **minimal required** set of permissions should be granted in each job.
permissions: {}
jobs:
check-codestyle-rust:
strategy:
matrix:
arch: ${{ fromJson(inputs.archs) }}
runs-on: ${{ fromJson(format('["self-hosted", "{0}"]', matrix.arch == 'arm64' && 'small-arm64' || 'small')) }}
container:
image: ${{ inputs.build-tools-image }}
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
options: --init
steps:
- name: Checkout
uses: actions/checkout@v4
with:
submodules: true
- name: Cache cargo deps
uses: actions/cache@v4
with:
path: |
~/.cargo/registry
!~/.cargo/registry/src
~/.cargo/git
target
key: v1-${{ runner.os }}-${{ runner.arch }}-cargo-${{ hashFiles('./Cargo.lock') }}-${{ hashFiles('./rust-toolchain.toml') }}-rust
# Some of our rust modules use FFI and need those to be checked
- name: Get postgres headers
run: make postgres-headers -j$(nproc)
# cargo hack runs the given cargo subcommand (clippy in this case) for all feature combinations.
# This will catch compiler & clippy warnings in all feature combinations.
# TODO: use cargo hack for build and test as well, but, that's quite expensive.
# NB: keep clippy args in sync with ./run_clippy.sh
#
# The only difference between "clippy --debug" and "clippy --release" is that in --release mode,
# #[cfg(debug_assertions)] blocks are not built. It's not worth building everything for second
# time just for that, so skip "clippy --release".
- run: |
CLIPPY_COMMON_ARGS="$( source .neon_clippy_args; echo "$CLIPPY_COMMON_ARGS")"
if [ "$CLIPPY_COMMON_ARGS" = "" ]; then
echo "No clippy args found in .neon_clippy_args"
exit 1
fi
echo "CLIPPY_COMMON_ARGS=${CLIPPY_COMMON_ARGS}" >> $GITHUB_ENV
- name: Run cargo clippy (debug)
run: cargo hack --features default --ignore-unknown-features --feature-powerset clippy $CLIPPY_COMMON_ARGS
- name: Check documentation generation
run: cargo doc --workspace --no-deps --document-private-items
env:
RUSTDOCFLAGS: "-Dwarnings -Arustdoc::private_intra_doc_links"
# Use `${{ !cancelled() }}` to run quck tests after the longer clippy run
- name: Check formatting
if: ${{ !cancelled() }}
run: cargo fmt --all -- --check
# https://github.com/facebookincubator/cargo-guppy/tree/bec4e0eb29dcd1faac70b1b5360267fc02bf830e/tools/cargo-hakari#2-keep-the-workspace-hack-up-to-date-in-ci
- name: Check rust dependencies
if: ${{ !cancelled() }}
run: |
cargo hakari generate --diff # workspace-hack Cargo.toml is up-to-date
cargo hakari manage-deps --dry-run # all workspace crates depend on workspace-hack

View File

@@ -1,79 +0,0 @@
name: Create Release PR
on:
workflow_call:
inputs:
component-name:
description: 'Component name'
required: true
type: string
release-branch:
description: 'Release branch'
required: true
type: string
secrets:
ci-access-token:
description: 'CI access token'
required: true
defaults:
run:
shell: bash -euo pipefail {0}
jobs:
create-release-branch:
runs-on: ubuntu-22.04
permissions:
contents: write # for `git push`
steps:
- uses: actions/checkout@v4
with:
ref: main
- name: Set variables
id: vars
env:
COMPONENT_NAME: ${{ inputs.component-name }}
RELEASE_BRANCH: ${{ inputs.release-branch }}
run: |
today=$(date +'%Y-%m-%d')
echo "title=${COMPONENT_NAME} release ${today}" | tee -a ${GITHUB_OUTPUT}
echo "rc-branch=rc/${RELEASE_BRANCH}/${today}" | tee -a ${GITHUB_OUTPUT}
- name: Configure git
run: |
git config user.name "github-actions[bot]"
git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
- name: Create RC branch
env:
RC_BRANCH: ${{ steps.vars.outputs.rc-branch }}
TITLE: ${{ steps.vars.outputs.title }}
run: |
git checkout -b "${RC_BRANCH}"
# create an empty commit to distinguish workflow runs
# from other possible releases from the same commit
git commit --allow-empty -m "${TITLE}"
git push origin "${RC_BRANCH}"
- name: Create a PR into ${{ inputs.release-branch }}
env:
GH_TOKEN: ${{ secrets.ci-access-token }}
RC_BRANCH: ${{ steps.vars.outputs.rc-branch }}
RELEASE_BRANCH: ${{ inputs.release-branch }}
TITLE: ${{ steps.vars.outputs.title }}
run: |
cat << EOF > body.md
## ${TITLE}
**Please merge this Pull Request using 'Create a merge commit' button**
EOF
gh pr create --title "${TITLE}" \
--body-file "body.md" \
--head "${RC_BRANCH}" \
--base "${RELEASE_BRANCH}"

View File

@@ -33,7 +33,7 @@ jobs:
# SC2086 - Double quote to prevent globbing and word splitting. - https://www.shellcheck.net/wiki/SC2086
SHELLCHECK_OPTS: --exclude=SC2046,SC2086
with:
fail_level: error
fail_on_error: true
filter_mode: nofilter
level: error

View File

@@ -67,9 +67,9 @@ jobs:
- uses: actions/checkout@v4
with:
ref: ${{ github.event.pull_request.head.sha }}
ref: main
token: ${{ secrets.CI_ACCESS_TOKEN }}
- name: Look for existing PR
id: get-pr
env:
@@ -77,7 +77,7 @@ jobs:
run: |
ALREADY_CREATED="$(gh pr --repo ${GITHUB_REPOSITORY} list --head ${BRANCH} --base main --json number --jq '.[].number')"
echo "ALREADY_CREATED=${ALREADY_CREATED}" >> ${GITHUB_OUTPUT}
- name: Get changed labels
id: get-labels
if: steps.get-pr.outputs.ALREADY_CREATED != ''
@@ -94,6 +94,8 @@ jobs:
echo "LABELS_TO_ADD=${LABELS_TO_ADD}" >> ${GITHUB_OUTPUT}
echo "LABELS_TO_REMOVE=${LABELS_TO_REMOVE}" >> ${GITHUB_OUTPUT}
- run: gh pr checkout "${PR_NUMBER}"
- run: git checkout -b "${BRANCH}"
- run: git push --force origin "${BRANCH}"
@@ -101,7 +103,7 @@ jobs:
- name: Create a Pull Request for CI run (if required)
if: steps.get-pr.outputs.ALREADY_CREATED == ''
env:
env:
GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
run: |
cat << EOF > body.md
@@ -138,7 +140,7 @@ jobs:
- run: git push --force origin "${BRANCH}"
if: steps.get-pr.outputs.ALREADY_CREATED != ''
cleanup:
# Close PRs and delete branchs if the original PR is closed.

View File

@@ -63,15 +63,11 @@ jobs:
fail-fast: false
matrix:
include:
- PG_VERSION: 16
- DEFAULT_PG_VERSION: 16
PLATFORM: "neon-staging"
region_id: ${{ github.event.inputs.region_id || 'aws-us-east-2' }}
RUNNER: [ self-hosted, us-east-2, x64 ]
- PG_VERSION: 17
PLATFORM: "neon-staging"
region_id: ${{ github.event.inputs.region_id || 'aws-us-east-2' }}
RUNNER: [ self-hosted, us-east-2, x64 ]
- PG_VERSION: 16
- DEFAULT_PG_VERSION: 16
PLATFORM: "azure-staging"
region_id: 'azure-eastus2'
RUNNER: [ self-hosted, eastus2, x64 ]
@@ -79,7 +75,7 @@ jobs:
TEST_PG_BENCH_DURATIONS_MATRIX: "300"
TEST_PG_BENCH_SCALES_MATRIX: "10,100"
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
PG_VERSION: ${{ matrix.PG_VERSION }}
DEFAULT_PG_VERSION: ${{ matrix.DEFAULT_PG_VERSION }}
TEST_OUTPUT: /tmp/test_output
BUILD_TYPE: remote
SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref_name == 'main' ) }}
@@ -109,14 +105,13 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Create Neon Project
id: create-neon-project
uses: ./.github/actions/neon-project-create
with:
region_id: ${{ matrix.region_id }}
postgres_version: ${{ env.PG_VERSION }}
postgres_version: ${{ env.DEFAULT_PG_VERSION }}
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
- name: Run benchmark
@@ -126,8 +121,7 @@ jobs:
test_selection: performance
run_in_parallel: false
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
pg_version: ${{ env.PG_VERSION }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
pg_version: ${{ env.DEFAULT_PG_VERSION }}
# Set --sparse-ordering option of pytest-order plugin
# to ensure tests are running in order of appears in the file.
# It's important for test_perf_pgbench.py::test_pgbench_remote_* tests
@@ -139,7 +133,6 @@ jobs:
--ignore test_runner/performance/test_perf_pgvector_queries.py
--ignore test_runner/performance/test_logical_replication.py
--ignore test_runner/performance/test_physical_replication.py
--ignore test_runner/performance/test_perf_ingest_using_pgcopydb.py
env:
BENCHMARK_CONNSTR: ${{ steps.create-neon-project.outputs.dsn }}
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
@@ -156,14 +149,12 @@ jobs:
id: create-allure-report
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
with:
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@v1
with:
channel-id: "C06KHQVQ7U3" # on-call-qa-staging-stream
channel-id: "C033QLM5P7D" # dev-staging-stream
slack-message: |
Periodic perf testing: ${{ job.status }}
<${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}|GitHub Run>
@@ -209,7 +200,6 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Run Logical Replication benchmarks
uses: ./.github/actions/run-python-test-set
@@ -220,7 +210,6 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 5400
pg_version: ${{ env.DEFAULT_PG_VERSION }}
aws-oicd-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 }}"
@@ -237,7 +226,6 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 5400
pg_version: ${{ env.DEFAULT_PG_VERSION }}
aws-oicd-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 }}"
@@ -249,13 +237,11 @@ jobs:
uses: ./.github/actions/allure-report-generate
with:
store-test-results-into-db: true
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
# Post both success and failure to the Slack channel
- name: Post to a Slack channel
if: ${{ github.event.schedule && !cancelled() }}
if: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@v1
with:
channel-id: "C06T9AMNDQQ" # on-call-compute-staging-stream
@@ -312,16 +298,11 @@ jobs:
"image": [ "'"$image_default"'" ],
"include": [{ "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-freetier", "db_size": "3gb" ,"runner": '"$runner_default"', "image": "'"$image_default"'" },
{ "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-new", "db_size": "10gb","runner": '"$runner_default"', "image": "'"$image_default"'" },
{ "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-new-many-tables","db_size": "10gb","runner": '"$runner_default"', "image": "'"$image_default"'" },
{ "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-new", "db_size": "50gb","runner": '"$runner_default"', "image": "'"$image_default"'" },
{ "pg_version": 16, "region_id": "azure-eastus2", "platform": "neonvm-azure-captest-freetier", "db_size": "3gb" ,"runner": '"$runner_azure"', "image": "neondatabase/build-tools:pinned-bookworm" },
{ "pg_version": 16, "region_id": "azure-eastus2", "platform": "neonvm-azure-captest-new", "db_size": "10gb","runner": '"$runner_azure"', "image": "neondatabase/build-tools:pinned-bookworm" },
{ "pg_version": 16, "region_id": "azure-eastus2", "platform": "neonvm-azure-captest-new", "db_size": "50gb","runner": '"$runner_azure"', "image": "neondatabase/build-tools:pinned-bookworm" },
{ "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-sharding-reuse", "db_size": "50gb","runner": '"$runner_default"', "image": "'"$image_default"'" },
{ "pg_version": 17, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-freetier", "db_size": "3gb" ,"runner": '"$runner_default"', "image": "'"$image_default"'" },
{ "pg_version": 17, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-new", "db_size": "10gb","runner": '"$runner_default"', "image": "'"$image_default"'" },
{ "pg_version": 17, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-new-many-tables","db_size": "10gb","runner": '"$runner_default"', "image": "'"$image_default"'" },
{ "pg_version": 17, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-new", "db_size": "50gb","runner": '"$runner_default"', "image": "'"$image_default"'" }]
{ "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-sharding-reuse", "db_size": "50gb","runner": '"$runner_default"', "image": "'"$image_default"'" }]
}'
if [ "$(date +%A)" = "Saturday" ] || [ ${RUN_AWS_RDS_AND_AURORA} = "true" ]; then
@@ -337,15 +318,12 @@ jobs:
matrix='{
"platform": [
"neonvm-captest-reuse"
],
"pg_version" : [
16,17
]
}'
if [ "$(date +%A)" = "Saturday" ] || [ ${RUN_AWS_RDS_AND_AURORA} = "true" ]; then
matrix=$(echo "$matrix" | jq '.include += [{ "pg_version": 16, "platform": "rds-postgres" },
{ "pg_version": 16, "platform": "rds-aurora" }]')
matrix=$(echo "$matrix" | jq '.include += [{ "platform": "rds-postgres" },
{ "platform": "rds-aurora" }]')
fi
echo "matrix=$(echo "$matrix" | jq --compact-output '.')" >> $GITHUB_OUTPUT
@@ -357,14 +335,14 @@ jobs:
"platform": [
"neonvm-captest-reuse"
],
"pg_version" : [
16,17
"scale": [
"10"
]
}'
if [ "$(date +%A)" = "Saturday" ] || [ ${RUN_AWS_RDS_AND_AURORA} = "true" ]; then
matrix=$(echo "$matrix" | jq '.include += [{ "pg_version": 16, "platform": "rds-postgres" },
{ "pg_version": 16, "platform": "rds-aurora" }]')
matrix=$(echo "$matrix" | jq '.include += [{ "platform": "rds-postgres", "scale": "10" },
{ "platform": "rds-aurora", "scale": "10" }]')
fi
echo "matrix=$(echo "$matrix" | jq --compact-output '.')" >> $GITHUB_OUTPUT
@@ -389,7 +367,7 @@ jobs:
TEST_PG_BENCH_DURATIONS_MATRIX: "60m"
TEST_PG_BENCH_SCALES_MATRIX: ${{ matrix.db_size }}
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
PG_VERSION: ${{ matrix.pg_version }}
DEFAULT_PG_VERSION: ${{ matrix.pg_version }}
TEST_OUTPUT: /tmp/test_output
BUILD_TYPE: remote
SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref_name == 'main' ) }}
@@ -419,15 +397,14 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Create Neon Project
if: contains(fromJson('["neonvm-captest-new", "neonvm-captest-new-many-tables", "neonvm-captest-freetier", "neonvm-azure-captest-freetier", "neonvm-azure-captest-new"]'), matrix.platform)
if: contains(fromJson('["neonvm-captest-new", "neonvm-captest-freetier", "neonvm-azure-captest-freetier", "neonvm-azure-captest-new"]'), matrix.platform)
id: create-neon-project
uses: ./.github/actions/neon-project-create
with:
region_id: ${{ matrix.region_id }}
postgres_version: ${{ env.PG_VERSION }}
postgres_version: ${{ env.DEFAULT_PG_VERSION }}
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
compute_units: ${{ (contains(matrix.platform, 'captest-freetier') && '[0.25, 0.25]') || '[1, 1]' }}
@@ -441,7 +418,7 @@ jobs:
neonvm-captest-sharding-reuse)
CONNSTR=${{ secrets.BENCHMARK_CAPTEST_SHARDING_CONNSTR }}
;;
neonvm-captest-new | neonvm-captest-new-many-tables | neonvm-captest-freetier | neonvm-azure-captest-new | neonvm-azure-captest-freetier)
neonvm-captest-new | neonvm-captest-freetier | neonvm-azure-captest-new | neonvm-azure-captest-freetier)
CONNSTR=${{ steps.create-neon-project.outputs.dsn }}
;;
rds-aurora)
@@ -458,26 +435,6 @@ jobs:
echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
# we want to compare Neon project OLTP throughput and latency at scale factor 10 GB
# without (neonvm-captest-new)
# and with (neonvm-captest-new-many-tables) many relations in the database
- name: Create many relations before the run
if: contains(fromJson('["neonvm-captest-new-many-tables"]'), matrix.platform)
uses: ./.github/actions/run-python-test-set
with:
build_type: ${{ env.BUILD_TYPE }}
test_selection: performance
run_in_parallel: false
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_perf_many_relations
pg_version: ${{ env.PG_VERSION }}
aws-oicd-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 }}"
TEST_NUM_RELATIONS: 10000
- name: Benchmark init
uses: ./.github/actions/run-python-test-set
with:
@@ -486,8 +443,7 @@ jobs:
run_in_parallel: false
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_init
pg_version: ${{ env.PG_VERSION }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
pg_version: ${{ env.DEFAULT_PG_VERSION }}
env:
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
@@ -501,8 +457,7 @@ jobs:
run_in_parallel: false
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_simple_update
pg_version: ${{ env.PG_VERSION }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
pg_version: ${{ env.DEFAULT_PG_VERSION }}
env:
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
@@ -516,8 +471,7 @@ jobs:
run_in_parallel: false
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_select_only
pg_version: ${{ env.PG_VERSION }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
pg_version: ${{ env.DEFAULT_PG_VERSION }}
env:
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
@@ -534,14 +488,12 @@ jobs:
id: create-allure-report
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
with:
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@v1
with:
channel-id: "C06KHQVQ7U3" # on-call-qa-staging-stream
channel-id: "C033QLM5P7D" # dev-staging-stream
slack-message: |
Periodic perf testing on ${{ matrix.platform }}: ${{ job.status }}
<${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}|GitHub Run>
@@ -560,19 +512,14 @@ jobs:
include:
- PLATFORM: "neonvm-captest-pgvector"
RUNNER: [ self-hosted, us-east-2, x64 ]
postgres_version: 16
- PLATFORM: "neonvm-captest-pgvector-pg17"
RUNNER: [ self-hosted, us-east-2, x64 ]
postgres_version: 17
- PLATFORM: "azure-captest-pgvector"
RUNNER: [ self-hosted, eastus2, x64 ]
postgres_version: 16
env:
TEST_PG_BENCH_DURATIONS_MATRIX: "15m"
TEST_PG_BENCH_SCALES_MATRIX: "1"
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
PG_VERSION: ${{ matrix.postgres_version }}
DEFAULT_PG_VERSION: 16
TEST_OUTPUT: /tmp/test_output
BUILD_TYPE: remote
@@ -581,7 +528,7 @@ jobs:
runs-on: ${{ matrix.RUNNER }}
container:
image: neondatabase/build-tools:pinned-bookworm
image: neondatabase/build-tools:pinned
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
@@ -590,20 +537,32 @@ jobs:
steps:
- uses: actions/checkout@v4
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 18000 # 5 hours
# until https://github.com/neondatabase/neon/issues/8275 is fixed we temporarily install postgresql-16
# instead of using Neon artifacts containing pgbench
- name: Install postgresql-16 where pytest expects it
run: |
# Just to make it easier to test things locally on macOS (with arm64)
arch=$(uname -m | sed 's/x86_64/amd64/g' | sed 's/aarch64/arm64/g')
- name: Download Neon artifact
uses: ./.github/actions/download
with:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
cd /home/nonroot
wget -q "https://apt.postgresql.org/pub/repos/apt/pool/main/p/postgresql-17/libpq5_17.0-1.pgdg110+1_${arch}.deb"
wget -q "https://apt.postgresql.org/pub/repos/apt/pool/main/p/postgresql-16/postgresql-client-16_16.4-1.pgdg110+2_${arch}.deb"
wget -q "https://apt.postgresql.org/pub/repos/apt/pool/main/p/postgresql-16/postgresql-16_16.4-1.pgdg110+2_${arch}.deb"
dpkg -x libpq5_17.0-1.pgdg110+1_${arch}.deb pg
dpkg -x postgresql-16_16.4-1.pgdg110+2_${arch}.deb pg
dpkg -x postgresql-client-16_16.4-1.pgdg110+2_${arch}.deb pg
mkdir -p /tmp/neon/pg_install/v16/bin
ln -s /home/nonroot/pg/usr/lib/postgresql/16/bin/pgbench /tmp/neon/pg_install/v16/bin/pgbench
ln -s /home/nonroot/pg/usr/lib/postgresql/16/bin/psql /tmp/neon/pg_install/v16/bin/psql
ln -s /home/nonroot/pg/usr/lib/$(uname -m)-linux-gnu /tmp/neon/pg_install/v16/lib
LD_LIBRARY_PATH="/home/nonroot/pg/usr/lib/$(uname -m)-linux-gnu:${LD_LIBRARY_PATH:-}"
export LD_LIBRARY_PATH
echo "LD_LIBRARY_PATH=${LD_LIBRARY_PATH}" >> ${GITHUB_ENV}
/tmp/neon/pg_install/v16/bin/pgbench --version
/tmp/neon/pg_install/v16/bin/psql --version
- name: Set up Connection String
id: set-up-connstr
@@ -612,9 +571,6 @@ jobs:
neonvm-captest-pgvector)
CONNSTR=${{ secrets.BENCHMARK_PGVECTOR_CONNSTR }}
;;
neonvm-captest-pgvector-pg17)
CONNSTR=${{ secrets.BENCHMARK_PGVECTOR_CONNSTR_PG17 }}
;;
azure-captest-pgvector)
CONNSTR=${{ secrets.BENCHMARK_PGVECTOR_CONNSTR_AZURE }}
;;
@@ -626,6 +582,13 @@ jobs:
echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 18000 # 5 hours
- name: Benchmark pgvector hnsw indexing
uses: ./.github/actions/run-python-test-set
with:
@@ -634,8 +597,7 @@ jobs:
run_in_parallel: false
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_pgvector_indexing
pg_version: ${{ env.PG_VERSION }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
pg_version: ${{ env.DEFAULT_PG_VERSION }}
env:
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
@@ -649,8 +611,7 @@ jobs:
run_in_parallel: false
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600
pg_version: ${{ env.PG_VERSION }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
pg_version: ${{ env.DEFAULT_PG_VERSION }}
env:
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
@@ -660,14 +621,12 @@ jobs:
id: create-allure-report
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
with:
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@v1
with:
channel-id: "C06KHQVQ7U3" # on-call-qa-staging-stream
channel-id: "C033QLM5P7D" # dev-staging-stream
slack-message: |
Periodic perf testing on ${{ env.PLATFORM }}: ${{ job.status }}
<${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}|GitHub Run>
@@ -696,7 +655,7 @@ jobs:
env:
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
PG_VERSION: ${{ matrix.pg_version }}
DEFAULT_PG_VERSION: 16
TEST_OUTPUT: /tmp/test_output
TEST_OLAP_COLLECT_EXPLAIN: ${{ github.event.inputs.collect_olap_explain }}
TEST_OLAP_COLLECT_PG_STAT_STATEMENTS: ${{ github.event.inputs.collect_pg_stat_statements }}
@@ -732,25 +691,13 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Set up Connection String
id: set-up-connstr
run: |
case "${PLATFORM}" in
neonvm-captest-reuse)
case "${PG_VERSION}" in
16)
CONNSTR=${{ secrets.BENCHMARK_CAPTEST_CLICKBENCH_10M_CONNSTR }}
;;
17)
CONNSTR=${{ secrets.BENCHMARK_CAPTEST_CLICKBENCH_CONNSTR_PG17 }}
;;
*)
echo >&2 "Unsupported PG_VERSION=${PG_VERSION} for PLATFORM=${PLATFORM}"
exit 1
;;
esac
CONNSTR=${{ secrets.BENCHMARK_CAPTEST_CLICKBENCH_10M_CONNSTR }}
;;
rds-aurora)
CONNSTR=${{ secrets.BENCHMARK_RDS_AURORA_CLICKBENCH_10M_CONNSTR }}
@@ -774,8 +721,7 @@ jobs:
run_in_parallel: false
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 43200 -k test_clickbench
pg_version: ${{ env.PG_VERSION }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
pg_version: ${{ env.DEFAULT_PG_VERSION }}
env:
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
@@ -788,14 +734,12 @@ jobs:
id: create-allure-report
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
with:
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@v1
with:
channel-id: "C06KHQVQ7U3" # on-call-qa-staging-stream
channel-id: "C033QLM5P7D" # dev-staging-stream
slack-message: |
Periodic OLAP perf testing on ${{ matrix.platform }}: ${{ job.status }}
<${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}|GitHub Run>
@@ -810,7 +754,7 @@ jobs:
# We might change it after https://github.com/neondatabase/neon/issues/2900.
#
# *_TPCH_S10_CONNSTR: DB generated with scale factor 10 (~10 GB)
# if: ${{ !cancelled() && (github.event.inputs.run_only_pgvector_tests == 'false' || github.event.inputs.run_only_pgvector_tests == null) }}
if: ${{ !cancelled() && (github.event.inputs.run_only_pgvector_tests == 'false' || github.event.inputs.run_only_pgvector_tests == null) }}
permissions:
contents: write
statuses: write
@@ -823,11 +767,12 @@ jobs:
env:
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
PG_VERSION: ${{ matrix.pg_version }}
DEFAULT_PG_VERSION: 16
TEST_OUTPUT: /tmp/test_output
BUILD_TYPE: remote
SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref_name == 'main' ) }}
PLATFORM: ${{ matrix.platform }}
TEST_OLAP_SCALE: ${{ matrix.scale }}
runs-on: [ self-hosted, us-east-2, x64 ]
container:
@@ -853,30 +798,18 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Get Connstring Secret Name
run: |
case "${PLATFORM}" in
neonvm-captest-reuse)
case "${PG_VERSION}" in
16)
CONNSTR_SECRET_NAME="BENCHMARK_CAPTEST_TPCH_S10_CONNSTR"
;;
17)
CONNSTR_SECRET_NAME="BENCHMARK_CAPTEST_TPCH_CONNSTR_PG17"
;;
*)
echo >&2 "Unsupported PG_VERSION=${PG_VERSION} for PLATFORM=${PLATFORM}"
exit 1
;;
esac
ENV_PLATFORM=CAPTEST_TPCH
;;
rds-aurora)
CONNSTR_SECRET_NAME="BENCHMARK_RDS_AURORA_TPCH_S10_CONNSTR"
ENV_PLATFORM=RDS_AURORA_TPCH
;;
rds-postgres)
CONNSTR_SECRET_NAME="BENCHMARK_RDS_POSTGRES_TPCH_S10_CONNSTR"
ENV_PLATFORM=RDS_POSTGRES_TPCH
;;
*)
echo >&2 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neonvm-captest-reuse', 'rds-aurora', or 'rds-postgres'"
@@ -884,6 +817,7 @@ jobs:
;;
esac
CONNSTR_SECRET_NAME="BENCHMARK_${ENV_PLATFORM}_S${TEST_OLAP_SCALE}_CONNSTR"
echo "CONNSTR_SECRET_NAME=${CONNSTR_SECRET_NAME}" >> $GITHUB_ENV
- name: Set up Connection String
@@ -901,26 +835,23 @@ jobs:
run_in_parallel: false
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_tpch
pg_version: ${{ env.PG_VERSION }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
pg_version: ${{ env.DEFAULT_PG_VERSION }}
env:
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
TEST_OLAP_SCALE: 10
TEST_OLAP_SCALE: ${{ matrix.scale }}
- name: Create Allure report
id: create-allure-report
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
with:
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@v1
with:
channel-id: "C06KHQVQ7U3" # on-call-qa-staging-stream
channel-id: "C033QLM5P7D" # dev-staging-stream
slack-message: |
Periodic TPC-H perf testing on ${{ matrix.platform }}: ${{ job.status }}
<${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}|GitHub Run>
@@ -929,7 +860,7 @@ jobs:
SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
user-examples-compare:
# if: ${{ !cancelled() && (github.event.inputs.run_only_pgvector_tests == 'false' || github.event.inputs.run_only_pgvector_tests == null) }}
if: ${{ !cancelled() && (github.event.inputs.run_only_pgvector_tests == 'false' || github.event.inputs.run_only_pgvector_tests == null) }}
permissions:
contents: write
statuses: write
@@ -942,7 +873,7 @@ jobs:
env:
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
PG_VERSION: ${{ matrix.pg_version }}
DEFAULT_PG_VERSION: 16
TEST_OUTPUT: /tmp/test_output
BUILD_TYPE: remote
SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref_name == 'main' ) }}
@@ -972,25 +903,13 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Set up Connection String
id: set-up-connstr
run: |
case "${PLATFORM}" in
neonvm-captest-reuse)
case "${PG_VERSION}" in
16)
CONNSTR=${{ secrets.BENCHMARK_USER_EXAMPLE_CAPTEST_CONNSTR }}
;;
17)
CONNSTR=${{ secrets.BENCHMARK_CAPTEST_USER_EXAMPLE_CONNSTR_PG17 }}
;;
*)
echo >&2 "Unsupported PG_VERSION=${PG_VERSION} for PLATFORM=${PLATFORM}"
exit 1
;;
esac
CONNSTR=${{ secrets.BENCHMARK_USER_EXAMPLE_CAPTEST_CONNSTR }}
;;
rds-aurora)
CONNSTR=${{ secrets.BENCHMARK_USER_EXAMPLE_RDS_AURORA_CONNSTR }}
@@ -1014,8 +933,7 @@ jobs:
run_in_parallel: false
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_user_examples
pg_version: ${{ env.PG_VERSION }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
pg_version: ${{ env.DEFAULT_PG_VERSION }}
env:
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
@@ -1025,14 +943,12 @@ jobs:
id: create-allure-report
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
with:
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@v1
with:
channel-id: "C06KHQVQ7U3" # on-call-qa-staging-stream
channel-id: "C033QLM5P7D" # dev-staging-stream
slack-message: |
Periodic TPC-H perf testing on ${{ matrix.platform }}: ${{ job.status }}
<${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}|GitHub Run>

View File

@@ -3,23 +3,17 @@ name: Build build-tools image
on:
workflow_call:
inputs:
archs:
description: "Json array of architectures to build"
# Default values are set in `check-image` job, `set-variables` step
image-tag:
description: "build-tools image tag"
required: true
type: string
required: false
debians:
description: "Json array of Debian versions to build"
# Default values are set in `check-image` job, `set-variables` step
type: string
required: false
outputs:
image-tag:
description: "build-tools tag"
value: ${{ jobs.check-image.outputs.tag }}
value: ${{ inputs.image-tag }}
image:
description: "build-tools image"
value: neondatabase/build-tools:${{ jobs.check-image.outputs.tag }}
value: neondatabase/build-tools:${{ inputs.image-tag }}
defaults:
run:
@@ -41,48 +35,7 @@ permissions: {}
jobs:
check-image:
runs-on: ubuntu-22.04
outputs:
archs: ${{ steps.set-variables.outputs.archs }}
debians: ${{ steps.set-variables.outputs.debians }}
tag: ${{ steps.set-variables.outputs.image-tag }}
everything: ${{ steps.set-more-variables.outputs.everything }}
found: ${{ steps.set-more-variables.outputs.found }}
steps:
- uses: actions/checkout@v4
- name: Set variables
id: set-variables
env:
ARCHS: ${{ inputs.archs || '["x64","arm64"]' }}
DEBIANS: ${{ inputs.debians || '["bullseye","bookworm"]' }}
IMAGE_TAG: |
${{ hashFiles('build-tools.Dockerfile',
'.github/workflows/build-build-tools-image.yml') }}
run: |
echo "archs=${ARCHS}" | tee -a ${GITHUB_OUTPUT}
echo "debians=${DEBIANS}" | tee -a ${GITHUB_OUTPUT}
echo "image-tag=${IMAGE_TAG}" | tee -a ${GITHUB_OUTPUT}
- name: Set more variables
id: set-more-variables
env:
IMAGE_TAG: ${{ steps.set-variables.outputs.image-tag }}
EVERYTHING: |
${{ contains(fromJson(steps.set-variables.outputs.archs), 'x64') &&
contains(fromJson(steps.set-variables.outputs.archs), 'arm64') &&
contains(fromJson(steps.set-variables.outputs.debians), 'bullseye') &&
contains(fromJson(steps.set-variables.outputs.debians), 'bookworm') }}
run: |
if docker manifest inspect neondatabase/build-tools:${IMAGE_TAG}; then
found=true
else
found=false
fi
echo "everything=${EVERYTHING}" | tee -a ${GITHUB_OUTPUT}
echo "found=${found}" | tee -a ${GITHUB_OUTPUT}
uses: ./.github/workflows/check-build-tools-image.yml
build-image:
needs: [ check-image ]
@@ -90,12 +43,25 @@ jobs:
strategy:
matrix:
arch: ${{ fromJson(needs.check-image.outputs.archs) }}
debian: ${{ fromJson(needs.check-image.outputs.debians) }}
debian-version: [ bullseye, bookworm ]
arch: [ x64, arm64 ]
runs-on: ${{ fromJson(format('["self-hosted", "{0}"]', matrix.arch == 'arm64' && 'large-arm64' || 'large')) }}
env:
IMAGE_TAG: ${{ inputs.image-tag }}
steps:
- name: Check `input.tag` is correct
env:
INPUTS_IMAGE_TAG: ${{ inputs.image-tag }}
CHECK_IMAGE_TAG : ${{ needs.check-image.outputs.image-tag }}
run: |
if [ "${INPUTS_IMAGE_TAG}" != "${CHECK_IMAGE_TAG}" ]; then
echo "'inputs.image-tag' (${INPUTS_IMAGE_TAG}) does not match the tag of the latest build-tools image 'inputs.image-tag' (${CHECK_IMAGE_TAG})"
exit 1
fi
- uses: actions/checkout@v4
- uses: neondatabase/dev-actions/set-docker-config-dir@6094485bf440001c94a94a3f9e221e81ff6b6193
@@ -122,14 +88,14 @@ jobs:
push: true
pull: true
build-args: |
DEBIAN_VERSION=${{ matrix.debian }}
cache-from: type=registry,ref=cache.neon.build/build-tools:cache-${{ matrix.debian }}-${{ matrix.arch }}
cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/build-tools:cache-{0}-{1},mode=max', matrix.debian, matrix.arch) || '' }}
DEBIAN_VERSION=${{ matrix.debian-version }}
cache-from: type=registry,ref=cache.neon.build/build-tools:cache-${{ matrix.debian-version }}-${{ matrix.arch }}
cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/build-tools:cache-{0}-{1},mode=max', matrix.debian-version, matrix.arch) || '' }}
tags: |
neondatabase/build-tools:${{ needs.check-image.outputs.tag }}-${{ matrix.debian }}-${{ matrix.arch }}
neondatabase/build-tools:${{ inputs.image-tag }}-${{ matrix.debian-version }}-${{ matrix.arch }}
merge-images:
needs: [ check-image, build-image ]
needs: [ build-image ]
runs-on: ubuntu-22.04
steps:
@@ -140,22 +106,16 @@ jobs:
- name: Create multi-arch image
env:
DEFAULT_DEBIAN_VERSION: bookworm
ARCHS: ${{ join(fromJson(needs.check-image.outputs.archs), ' ') }}
DEBIANS: ${{ join(fromJson(needs.check-image.outputs.debians), ' ') }}
EVERYTHING: ${{ needs.check-image.outputs.everything }}
IMAGE_TAG: ${{ needs.check-image.outputs.tag }}
DEFAULT_DEBIAN_VERSION: bullseye
IMAGE_TAG: ${{ inputs.image-tag }}
run: |
for debian in ${DEBIANS}; do
tags=("-t" "neondatabase/build-tools:${IMAGE_TAG}-${debian}")
if [ "${EVERYTHING}" == "true" ] && [ "${debian}" == "${DEFAULT_DEBIAN_VERSION}" ]; then
for debian_version in bullseye bookworm; do
tags=("-t" "neondatabase/build-tools:${IMAGE_TAG}-${debian_version}")
if [ "${debian_version}" == "${DEFAULT_DEBIAN_VERSION}" ]; then
tags+=("-t" "neondatabase/build-tools:${IMAGE_TAG}")
fi
for arch in ${ARCHS}; do
tags+=("neondatabase/build-tools:${IMAGE_TAG}-${debian}-${arch}")
done
docker buildx imagetools create "${tags[@]}"
docker buildx imagetools create "${tags[@]}" \
neondatabase/build-tools:${IMAGE_TAG}-${debian_version}-x64 \
neondatabase/build-tools:${IMAGE_TAG}-${debian_version}-arm64
done

View File

@@ -1,241 +0,0 @@
name: Check neon with MacOS builds
on:
workflow_call:
inputs:
pg_versions:
description: "Array of the pg versions to build for, for example: ['v14', 'v17']"
type: string
default: '[]'
required: false
rebuild_rust_code:
description: "Rebuild Rust code"
type: boolean
default: false
required: false
rebuild_everything:
description: "If true, rebuild for all versions"
type: boolean
default: false
required: false
env:
RUST_BACKTRACE: 1
COPT: '-Werror'
# TODO: move `check-*` and `files-changed` jobs to the "Caller" Workflow
# We should care about that as Github has limitations:
# - You can connect up to four levels of workflows
# - You can call a maximum of 20 unique reusable workflows from a single workflow file.
# https://docs.github.com/en/actions/sharing-automations/reusing-workflows#limitations
jobs:
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: Checkout main repo
uses: actions/checkout@v4
- 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 ${{ matrix.postgres-version }} build
id: cache_pg
uses: actions/cache@v4
with:
path: pg_install/${{ 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$(sysctl -n hw.ncpu)
build-walproposer-lib:
if: |
(inputs.pg_versions != '[]' || inputs.rebuild_everything) && (
contains(github.event.pull_request.labels.*.name, 'run-extra-build-macos') ||
contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
github.ref_name == 'main'
)
timeout-minutes: 30
runs-on: macos-15
needs: [build-pgxn]
env:
# Use release build only, to have less debug info around
# Hence keeping target/ (and general cache size) smaller
BUILD_TYPE: release
steps:
- name: Checkout main repo
uses: actions/checkout@v4
- name: Set pg v17 for caching
id: pg_rev
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v17) | tee -a "${GITHUB_OUTPUT}"
- name: Cache postgres v17 build
id: cache_pg
uses: actions/cache@v4
with:
path: pg_install/v17
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-v17-${{ steps.pg_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Cache walproposer-lib
id: cache_walproposer_lib
uses: actions/cache@v4
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)
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: 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
BUILD_TYPE: release
steps:
- name: Checkout main repo
uses: actions/checkout@v4
with:
submodules: true
- name: Set pg v14 for caching
id: pg_rev_v14
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v14) | tee -a "${GITHUB_OUTPUT}"
- name: Set pg v15 for caching
id: pg_rev_v15
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v15) | tee -a "${GITHUB_OUTPUT}"
- name: Set pg v16 for caching
id: pg_rev_v16
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v16) | tee -a "${GITHUB_OUTPUT}"
- name: Set pg v17 for caching
id: pg_rev_v17
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v17) | tee -a "${GITHUB_OUTPUT}"
- name: Cache postgres v14 build
id: cache_pg
uses: actions/cache@v4
with:
path: pg_install/v14
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-v14-${{ steps.pg_rev_v14.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Cache postgres v15 build
id: cache_pg_v15
uses: actions/cache@v4
with:
path: pg_install/v15
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-v15-${{ steps.pg_rev_v15.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Cache postgres v16 build
id: cache_pg_v16
uses: actions/cache@v4
with:
path: pg_install/v16
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-v16-${{ steps.pg_rev_v16.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Cache postgres v17 build
id: cache_pg_v17
uses: actions/cache@v4
with:
path: pg_install/v17
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-v17-${{ steps.pg_rev_v17.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Cache cargo deps (only for v17)
uses: actions/cache@v4
with:
path: |
~/.cargo/registry
!~/.cargo/registry/src
~/.cargo/git
target
key: v1-${{ runner.os }}-${{ runner.arch }}-cargo-${{ hashFiles('./Cargo.lock') }}-${{ hashFiles('./rust-toolchain.toml') }}-rust
- name: Cache walproposer-lib
id: cache_walproposer_lib
uses: actions/cache@v4
with:
path: pg_install/build/walproposer-lib
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-walproposer_lib-v17-${{ steps.pg_rev_v17.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- 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' >> $GITHUB_ENV
- name: Run cargo build (only for v17)
run: cargo build --all --release -j$(sysctl -n hw.ncpu)
- name: Check that no warnings are produced (only for v17)
run: ./run_clippy.sh

View File

@@ -6,7 +6,6 @@ on:
- main
- release
- release-proxy
- release-compute
pull_request:
defaults:
@@ -21,6 +20,8 @@ concurrency:
env:
RUST_BACKTRACE: 1
COPT: '-Werror'
AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
# A concurrency group that we use for e2e-tests runs, matches `concurrency.group` above with `github.repository` as a prefix
E2E_CONCURRENCY_GROUP: ${{ github.repository }}-e2e-tests-${{ github.ref_name }}-${{ github.ref_name == 'main' && github.sha || 'anysha' }}
@@ -45,26 +46,6 @@ jobs:
run cancel-previous-in-concurrency-group.yml \
--field concurrency_group="${{ env.E2E_CONCURRENCY_GROUP }}"
files-changed:
needs: [ check-permissions ]
runs-on: [ self-hosted, small ]
timeout-minutes: 3
outputs:
check-rust-dependencies: ${{ steps.files-changed.outputs.rust_dependencies }}
steps:
- name: Checkout
uses: actions/checkout@v4
with:
submodules: true
- name: Check for file changes
uses: dorny/paths-filter@de90cc6fb38fc0963ad72b210f1f284cd68cea36 # v3.0.2
id: files-changed
with:
token: ${{ secrets.GITHUB_TOKEN }}
filters: .github/file-filters.yaml
tag:
needs: [ check-permissions ]
runs-on: [ self-hosted, small ]
@@ -89,18 +70,22 @@ jobs:
echo "tag=release-$(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 "GITHUB_REF_NAME (value '$GITHUB_REF_NAME') is not set to either 'main' or 'release'"
echo "tag=$GITHUB_RUN_ID" >> $GITHUB_OUTPUT
fi
shell: bash
id: build-tag
build-build-tools-image:
check-build-tools-image:
needs: [ check-permissions ]
uses: ./.github/workflows/check-build-tools-image.yml
build-build-tools-image:
needs: [ check-build-tools-image ]
uses: ./.github/workflows/build-build-tools-image.yml
with:
image-tag: ${{ needs.check-build-tools-image.outputs.image-tag }}
secrets: inherit
check-codestyle-python:
@@ -184,19 +169,77 @@ jobs:
check-codestyle-rust:
needs: [ check-permissions, build-build-tools-image ]
uses: ./.github/workflows/_check-codestyle-rust.yml
with:
build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
archs: '["x64", "arm64"]'
secrets: inherit
strategy:
matrix:
arch: [ x64, arm64 ]
runs-on: ${{ fromJson(format('["self-hosted", "{0}"]', matrix.arch == 'arm64' && 'small-arm64' || 'small')) }}
check-dependencies-rust:
needs: [ files-changed, build-build-tools-image ]
if: ${{ needs.files-changed.outputs.check-rust-dependencies == 'true' }}
uses: ./.github/workflows/cargo-deny.yml
with:
build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
secrets: inherit
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
options: --init
steps:
- name: Checkout
uses: actions/checkout@v4
with:
submodules: true
- name: Cache cargo deps
uses: actions/cache@v4
with:
path: |
~/.cargo/registry
!~/.cargo/registry/src
~/.cargo/git
target
key: v1-${{ runner.os }}-${{ runner.arch }}-cargo-${{ hashFiles('./Cargo.lock') }}-${{ hashFiles('./rust-toolchain.toml') }}-rust
# Some of our rust modules use FFI and need those to be checked
- name: Get postgres headers
run: make postgres-headers -j$(nproc)
# cargo hack runs the given cargo subcommand (clippy in this case) for all feature combinations.
# This will catch compiler & clippy warnings in all feature combinations.
# TODO: use cargo hack for build and test as well, but, that's quite expensive.
# NB: keep clippy args in sync with ./run_clippy.sh
#
# The only difference between "clippy --debug" and "clippy --release" is that in --release mode,
# #[cfg(debug_assertions)] blocks are not built. It's not worth building everything for second
# time just for that, so skip "clippy --release".
- run: |
CLIPPY_COMMON_ARGS="$( source .neon_clippy_args; echo "$CLIPPY_COMMON_ARGS")"
if [ "$CLIPPY_COMMON_ARGS" = "" ]; then
echo "No clippy args found in .neon_clippy_args"
exit 1
fi
echo "CLIPPY_COMMON_ARGS=${CLIPPY_COMMON_ARGS}" >> $GITHUB_ENV
- name: Run cargo clippy (debug)
run: cargo hack --feature-powerset clippy $CLIPPY_COMMON_ARGS
- name: Check documentation generation
run: cargo doc --workspace --no-deps --document-private-items
env:
RUSTDOCFLAGS: "-Dwarnings -Arustdoc::private_intra_doc_links"
# Use `${{ !cancelled() }}` to run quck tests after the longer clippy run
- name: Check formatting
if: ${{ !cancelled() }}
run: cargo fmt --all -- --check
# https://github.com/facebookincubator/cargo-guppy/tree/bec4e0eb29dcd1faac70b1b5360267fc02bf830e/tools/cargo-hakari#2-keep-the-workspace-hack-up-to-date-in-ci
- name: Check rust dependencies
if: ${{ !cancelled() }}
run: |
cargo hakari generate --diff # workspace-hack Cargo.toml is up-to-date
cargo hakari manage-deps --dry-run # all workspace crates depend on workspace-hack
# https://github.com/EmbarkStudios/cargo-deny
- name: Check rust licenses/bans/advisories/sources
if: ${{ !cancelled() }}
run: cargo deny check --hide-inclusion-graph
build-and-test-locally:
needs: [ tag, build-build-tools-image ]
@@ -215,15 +258,8 @@ jobs:
build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
build-tag: ${{ needs.tag.outputs.build-tag }}
build-type: ${{ matrix.build-type }}
# Run tests on all Postgres versions in release builds and only on the latest version in debug builds.
# Run without LFC on v17 release and debug builds only. For all the other cases LFC is enabled.
test-cfg: |
${{ matrix.build-type == 'release' && '[{"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":"v17", "lfc_state": "without-lfc"}]'
|| '[{"pg_version":"v17", "lfc_state": "without-lfc" }]' }}
# Run tests on all Postgres versions in release builds and only on the latest version in debug builds
pg-versions: ${{ matrix.build-type == 'release' && '["v14", "v15", "v16", "v17"]' || '["v17"]' }}
secrets: inherit
# Keep `benchmarks` job outside of `build-and-test-locally` workflow to make job failures non-blocking
@@ -265,12 +301,7 @@ jobs:
benchmarks:
if: github.ref_name == 'main' || contains(github.event.pull_request.labels.*.name, 'run-benchmarks')
needs: [ check-permissions, build-and-test-locally, build-build-tools-image, get-benchmarks-durations ]
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: write
pull-requests: write
runs-on: [ self-hosted, small-metal ]
runs-on: [ self-hosted, small ]
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
credentials:
@@ -298,7 +329,6 @@ jobs:
extra_params: --splits 5 --group ${{ matrix.pytest_split_group }}
benchmark_durations: ${{ needs.get-benchmarks-durations.outputs.json }}
pg_version: v16
aws-oicd-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 }}"
@@ -308,31 +338,24 @@ jobs:
# XXX: no coverage data handling here, since benchmarks are run on release builds,
# while coverage is currently collected for the debug ones
report-benchmarks-results-to-slack:
report-benchmarks-failures:
needs: [ benchmarks, create-test-report ]
if: github.ref_name == 'main' && !cancelled() && contains(fromJSON('["success", "failure"]'), needs.benchmarks.result)
if: github.ref_name == 'main' && failure() && needs.benchmarks.result == 'failure'
runs-on: ubuntu-22.04
steps:
- uses: slackapi/slack-github-action@v2
- uses: slackapi/slack-github-action@v1
with:
method: chat.postMessage
token: ${{ secrets.SLACK_BOT_TOKEN }}
payload: |
channel: "${{ vars.SLACK_ON_CALL_STORAGE_STAGING_STREAM }}"
text: |
Benchmarks on main: *${{ needs.benchmarks.result }}*
- <${{ needs.create-test-report.outputs.report-url }}|Allure report>
- <${{ github.event.head_commit.url }}|${{ github.sha }}>
channel-id: C060CNA47S9 # on-call-staging-storage-stream
slack-message: |
Benchmarks failed on main <${{ github.event.head_commit.url }}|${{ github.sha }}>
<${{ needs.create-test-report.outputs.report-url }}|Allure report>
env:
SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
create-test-report:
needs: [ check-permissions, build-and-test-locally, coverage-report, build-build-tools-image, benchmarks ]
if: ${{ !cancelled() && contains(fromJSON('["skipped", "success"]'), needs.check-permissions.result) }}
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 }}
@@ -353,7 +376,6 @@ jobs:
uses: ./.github/actions/allure-report-generate
with:
store-test-results-into-db: true
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
@@ -385,10 +407,6 @@ jobs:
coverage-report:
if: ${{ !startsWith(github.ref_name, 'release') }}
needs: [ check-permissions, build-build-tools-image, build-and-test-locally ]
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: write
runs-on: [ self-hosted, small ]
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
@@ -415,14 +433,12 @@ jobs:
with:
name: neon-${{ runner.os }}-${{ runner.arch }}-${{ matrix.build_type }}-artifact
path: /tmp/neon
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Get coverage artifact
uses: ./.github/actions/download
with:
name: coverage-data-artifact
path: /tmp/coverage
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Merge coverage data
run: scripts/coverage "--profraw-prefix=$GITHUB_JOB" --dir=/tmp/coverage merge
@@ -496,8 +512,8 @@ jobs:
})
trigger-e2e-tests:
if: ${{ !github.event.pull_request.draft || contains( github.event.pull_request.labels.*.name, 'run-e2e-tests-in-draft') || github.ref_name == 'main' || github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute' }}
needs: [ check-permissions, promote-images-dev, tag ]
if: ${{ !github.event.pull_request.draft || contains( github.event.pull_request.labels.*.name, 'run-e2e-tests-in-draft') || github.ref_name == 'main' || github.ref_name == 'release' || github.ref_name == 'release-proxy' }}
needs: [ check-permissions, promote-images, tag ]
uses: ./.github/workflows/trigger-e2e-tests.yml
secrets: inherit
@@ -553,10 +569,6 @@ jobs:
neon-image:
needs: [ neon-image-arch, tag ]
runs-on: ubuntu-22.04
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: read
steps:
- uses: docker/login-action@v3
@@ -571,15 +583,11 @@ jobs:
neondatabase/neon:${{ needs.tag.outputs.build-tag }}-bookworm-x64 \
neondatabase/neon:${{ needs.tag.outputs.build-tag }}-bookworm-arm64
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
- uses: docker/login-action@v3
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 3600
- name: Login to Amazon Dev ECR
uses: aws-actions/amazon-ecr-login@v2
registry: 369495373322.dkr.ecr.eu-central-1.amazonaws.com
username: ${{ secrets.AWS_ACCESS_KEY_DEV }}
password: ${{ secrets.AWS_SECRET_KEY_DEV }}
- name: Push multi-arch image to ECR
run: |
@@ -588,10 +596,6 @@ jobs:
compute-node-image-arch:
needs: [ check-permissions, build-build-tools-image, tag ]
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: read
strategy:
fail-fast: false
matrix:
@@ -632,15 +636,11 @@ jobs:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
- uses: docker/login-action@v3
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 3600
- name: Login to Amazon Dev ECR
uses: aws-actions/amazon-ecr-login@v2
registry: 369495373322.dkr.ecr.eu-central-1.amazonaws.com
username: ${{ secrets.AWS_ACCESS_KEY_DEV }}
password: ${{ secrets.AWS_SECRET_KEY_DEV }}
- uses: docker/login-action@v3
with:
@@ -668,7 +668,7 @@ jobs:
neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-${{ matrix.arch }}
- name: Build neon extensions test image
if: matrix.version.pg >= 'v16'
if: matrix.version.pg == 'v16'
uses: docker/build-push-action@v6
with:
context: .
@@ -682,17 +682,38 @@ jobs:
push: true
pull: true
file: compute/compute-node.Dockerfile
target: extension-tests
cache-from: type=registry,ref=cache.neon.build/compute-node-${{ matrix.version.pg }}:cache-${{ matrix.version.debian }}-${{ matrix.arch }}
target: neon-pg-ext-test
cache-from: type=registry,ref=cache.neon.build/neon-test-extensions-${{ matrix.version.pg }}:cache-${{ matrix.version.debian }}-${{ matrix.arch }}
cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/neon-test-extensions-{0}:cache-{1}-{2},mode=max', matrix.version.pg, matrix.version.debian, matrix.arch) || '' }}
tags: |
neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{needs.tag.outputs.build-tag}}-${{ matrix.version.debian }}-${{ matrix.arch }}
- name: Build compute-tools image
# compute-tools are Postgres independent, so build it only once
# We pick 16, because that builds on debian 11 with older glibc (and is
# thus compatible with newer glibc), rather than 17 on Debian 12, as
# that isn't guaranteed to be compatible with Debian 11
if: matrix.version.pg == 'v16'
uses: docker/build-push-action@v6
with:
target: compute-tools-image
context: .
build-args: |
GIT_VERSION=${{ github.event.pull_request.head.sha || github.sha }}
BUILD_TAG=${{ needs.tag.outputs.build-tag }}
TAG=${{ needs.build-build-tools-image.outputs.image-tag }}-${{ matrix.version.debian }}
DEBIAN_VERSION=${{ matrix.version.debian }}
provenance: false
push: true
pull: true
file: compute/compute-node.Dockerfile
cache-from: type=registry,ref=cache.neon.build/neon-test-extensions-${{ matrix.version.pg }}:cache-${{ matrix.version.debian }}-${{ matrix.arch }}
cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/compute-tools-{0}:cache-{1}-{2},mode=max', matrix.version.pg, matrix.version.debian, matrix.arch) || '' }}
tags: |
neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-${{ matrix.arch }}
compute-node-image:
needs: [ compute-node-image-arch, tag ]
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: read
runs-on: ubuntu-22.04
strategy:
@@ -722,28 +743,38 @@ jobs:
neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-arm64
- name: Create multi-arch neon-test-extensions image
if: matrix.version.pg >= 'v16'
if: matrix.version.pg == 'v16'
run: |
docker buildx imagetools create -t neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }} \
-t neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }} \
neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-x64 \
neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-arm64
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 3600
- name: Create multi-arch compute-tools image
if: matrix.version.pg == 'v16'
run: |
docker buildx imagetools create -t neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }} \
-t neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }} \
neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-x64 \
neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-arm64
- name: Login to Amazon Dev ECR
uses: aws-actions/amazon-ecr-login@v2
- uses: docker/login-action@v3
with:
registry: 369495373322.dkr.ecr.eu-central-1.amazonaws.com
username: ${{ secrets.AWS_ACCESS_KEY_DEV }}
password: ${{ secrets.AWS_SECRET_KEY_DEV }}
- name: Push multi-arch compute-node-${{ matrix.version.pg }} image to ECR
run: |
docker buildx imagetools create -t 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }} \
neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}
- name: Push multi-arch compute-tools image to ECR
if: matrix.version.pg == 'v16'
run: |
docker buildx imagetools create -t 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-tools:${{ needs.tag.outputs.build-tag }} \
neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}
vm-compute-node-image:
needs: [ check-permissions, tag, compute-node-image ]
runs-on: [ self-hosted, large ]
@@ -761,7 +792,7 @@ jobs:
- pg: v17
debian: bookworm
env:
VM_BUILDER_VERSION: v0.37.1
VM_BUILDER_VERSION: v0.35.0
steps:
- uses: actions/checkout@v4
@@ -801,7 +832,6 @@ jobs:
fail-fast: false
matrix:
arch: [ x64, arm64 ]
pg_version: [v16, v17]
runs-on: ${{ fromJson(format('["self-hosted", "{0}"]', matrix.arch == 'arm64' && 'small-arm64' || 'small')) }}
@@ -814,17 +844,6 @@ jobs:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
- name: Get the last compute release tag
id: get-last-compute-release-tag
env:
GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
run: |
tag=$(gh api -q '[.[].tag_name | select(startswith("release-compute"))][0]'\
-H "Accept: application/vnd.github+json" \
-H "X-GitHub-Api-Version: 2022-11-28" \
"/repos/${{ github.repository }}/releases")
echo tag=${tag} >> ${GITHUB_OUTPUT}
# `neondatabase/neon` contains multiple binaries, all of them use the same input for the version into the same version formatting library.
# Pick pageserver as currently the only binary with extra "version" features printed in the string to verify.
# Regular pageserver version string looks like
@@ -851,39 +870,20 @@ jobs:
- name: Verify docker-compose example and test extensions
timeout-minutes: 20
env:
TAG: ${{needs.tag.outputs.build-tag}}
TEST_VERSION_ONLY: ${{ matrix.pg_version }}
run: ./docker-compose/docker_compose_test.sh
- name: Print logs and clean up docker-compose test
if: always()
run: |
docker compose --profile test-extensions -f ./docker-compose/docker-compose.yml logs || true
docker compose --profile test-extensions -f ./docker-compose/docker-compose.yml down
- name: Test extension upgrade
timeout-minutes: 20
if: ${{ needs.tag.outputs.build-tag == github.run_id }}
env:
NEWTAG: ${{ needs.tag.outputs.build-tag }}
OLDTAG: ${{ steps.get-last-compute-release-tag.outputs.tag }}
run: ./docker-compose/test_extensions_upgrade.sh
run: env TAG=${{needs.tag.outputs.build-tag}} ./docker-compose/docker_compose_test.sh
- name: Print logs and clean up
if: always()
run: |
docker compose --profile test-extensions -f ./docker-compose/docker-compose.yml logs || true
docker compose --profile test-extensions -f ./docker-compose/docker-compose.yml down
docker compose -f ./docker-compose/docker-compose.yml logs || 0
docker compose -f ./docker-compose/docker-compose.yml down
promote-images-dev:
needs: [ check-permissions, tag, vm-compute-node-image, neon-image ]
promote-images:
needs: [ check-permissions, tag, test-images, vm-compute-node-image ]
runs-on: ubuntu-22.04
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: read
id-token: write # for `aws-actions/configure-aws-credentials`
env:
VERSIONS: v14 v15 v16 v17
@@ -894,15 +894,12 @@ jobs:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
- name: Login to dev ECR
uses: docker/login-action@v3
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 3600
- name: Login to Amazon Dev ECR
uses: aws-actions/amazon-ecr-login@v2
registry: 369495373322.dkr.ecr.eu-central-1.amazonaws.com
username: ${{ secrets.AWS_ACCESS_KEY_DEV }}
password: ${{ secrets.AWS_SECRET_KEY_DEV }}
- name: Copy vm-compute-node images to ECR
run: |
@@ -911,35 +908,6 @@ jobs:
neondatabase/vm-compute-node-${version}:${{ needs.tag.outputs.build-tag }}
done
promote-images-prod:
needs: [ check-permissions, tag, test-images, promote-images-dev ]
runs-on: ubuntu-22.04
if: github.ref_name == 'main' || github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: read
env:
VERSIONS: v14 v15 v16 v17
steps:
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 3600
- name: Login to Amazon Dev ECR
uses: aws-actions/amazon-ecr-login@v2
- uses: docker/login-action@v3
with:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
- name: Add latest tag to images
if: github.ref_name == 'main'
run: |
@@ -947,6 +915,9 @@ jobs:
docker buildx imagetools create -t $repo/neon:latest \
$repo/neon:${{ needs.tag.outputs.build-tag }}
docker buildx imagetools create -t $repo/compute-tools:latest \
$repo/compute-tools:${{ needs.tag.outputs.build-tag }}
for version in ${VERSIONS}; do
docker buildx imagetools create -t $repo/compute-node-${version}:latest \
$repo/compute-node-${version}:${{ needs.tag.outputs.build-tag }}
@@ -959,7 +930,7 @@ jobs:
neondatabase/neon-test-extensions-v16:${{ needs.tag.outputs.build-tag }}
- name: Configure AWS-prod credentials
if: github.ref_name == 'release'|| github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
if: github.ref_name == 'release'|| github.ref_name == 'release-proxy'
uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: eu-central-1
@@ -968,38 +939,38 @@ jobs:
- name: Login to prod ECR
uses: docker/login-action@v3
if: github.ref_name == 'release'|| github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
if: github.ref_name == 'release'|| github.ref_name == 'release-proxy'
with:
registry: 093970136003.dkr.ecr.eu-central-1.amazonaws.com
- name: Copy all images to prod ECR
if: github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
if: github.ref_name == 'release'|| github.ref_name == 'release-proxy'
run: |
for image in neon {vm-,}compute-node-{v14,v15,v16,v17}; do
for image in neon compute-tools {vm-,}compute-node-{v14,v15,v16,v17}; do
docker buildx imagetools create -t 093970136003.dkr.ecr.eu-central-1.amazonaws.com/${image}:${{ needs.tag.outputs.build-tag }} \
369495373322.dkr.ecr.eu-central-1.amazonaws.com/${image}:${{ needs.tag.outputs.build-tag }}
done
push-to-acr-dev:
if: github.ref_name == 'main'
needs: [ tag, promote-images-dev ]
needs: [ tag, promote-images ]
uses: ./.github/workflows/_push-to-acr.yml
with:
client_id: ${{ vars.AZURE_DEV_CLIENT_ID }}
image_tag: ${{ needs.tag.outputs.build-tag }}
images: neon vm-compute-node-v14 vm-compute-node-v15 vm-compute-node-v16 vm-compute-node-v17 compute-node-v14 compute-node-v15 compute-node-v16 compute-node-v17
images: neon compute-tools vm-compute-node-v14 vm-compute-node-v15 vm-compute-node-v16 vm-compute-node-v17 compute-node-v14 compute-node-v15 compute-node-v16 compute-node-v17
registry_name: ${{ vars.AZURE_DEV_REGISTRY_NAME }}
subscription_id: ${{ vars.AZURE_DEV_SUBSCRIPTION_ID }}
tenant_id: ${{ vars.AZURE_TENANT_ID }}
push-to-acr-prod:
if: github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
needs: [ tag, promote-images-prod ]
if: github.ref_name == 'release'|| github.ref_name == 'release-proxy'
needs: [ tag, promote-images ]
uses: ./.github/workflows/_push-to-acr.yml
with:
client_id: ${{ vars.AZURE_PROD_CLIENT_ID }}
image_tag: ${{ needs.tag.outputs.build-tag }}
images: neon vm-compute-node-v14 vm-compute-node-v15 vm-compute-node-v16 vm-compute-node-v17 compute-node-v14 compute-node-v15 compute-node-v16 compute-node-v17
images: neon compute-tools vm-compute-node-v14 vm-compute-node-v15 vm-compute-node-v16 vm-compute-node-v17 compute-node-v14 compute-node-v15 compute-node-v16 compute-node-v17
registry_name: ${{ vars.AZURE_PROD_REGISTRY_NAME }}
subscription_id: ${{ vars.AZURE_PROD_SUBSCRIPTION_ID }}
tenant_id: ${{ vars.AZURE_TENANT_ID }}
@@ -1007,11 +978,6 @@ jobs:
trigger-custom-extensions-build-and-wait:
needs: [ check-permissions, tag ]
runs-on: ubuntu-22.04
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: write
pull-requests: write
steps:
- name: Set PR's status to pending and request a remote CI test
run: |
@@ -1084,114 +1050,15 @@ jobs:
exit 1
deploy:
needs: [ check-permissions, promote-images-prod, tag, build-and-test-locally, trigger-custom-extensions-build-and-wait, push-to-acr-dev, push-to-acr-prod ]
needs: [ check-permissions, promote-images, tag, build-and-test-locally, trigger-custom-extensions-build-and-wait, push-to-acr-dev, push-to-acr-prod ]
# `!failure() && !cancelled()` is required because the workflow depends on the job that can be skipped: `push-to-acr-dev` and `push-to-acr-prod`
if: (github.ref_name == 'main' || github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute') && !failure() && !cancelled()
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: write
if: (github.ref_name == 'main' || github.ref_name == 'release' || github.ref_name == 'release-proxy') && !failure() && !cancelled()
runs-on: [ self-hosted, small ]
container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/ansible:latest
steps:
- uses: actions/checkout@v4
- name: Create git tag and GitHub release
if: github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
uses: actions/github-script@v7
with:
retries: 5
script: |
const tag = "${{ needs.tag.outputs.build-tag }}";
const branch = "${{ github.ref_name }}";
try {
const existingRef = await github.rest.git.getRef({
owner: context.repo.owner,
repo: context.repo.repo,
ref: `tags/${tag}`,
});
if (existingRef.data.object.sha !== context.sha) {
throw new Error(`Tag ${tag} already exists but points to a different commit (expected: ${context.sha}, actual: ${existingRef.data.object.sha}).`);
}
console.log(`Tag ${tag} already exists and points to ${context.sha} as expected.`);
} catch (error) {
if (error.status !== 404) {
throw error;
}
console.log(`Tag ${tag} does not exist. Creating it...`);
await github.rest.git.createRef({
owner: context.repo.owner,
repo: context.repo.repo,
ref: `refs/tags/${tag}`,
sha: context.sha,
});
console.log(`Tag ${tag} created successfully.`);
}
try {
const existingRelease = await github.rest.repos.getReleaseByTag({
owner: context.repo.owner,
repo: context.repo.repo,
tag: tag,
});
console.log(`Release for tag ${tag} already exists (ID: ${existingRelease.data.id}).`);
} catch (error) {
if (error.status !== 404) {
throw error;
}
console.log(`Release for tag ${tag} does not exist. Creating it...`);
// Find the PR number using the commit SHA
const pullRequests = await github.rest.pulls.list({
owner: context.repo.owner,
repo: context.repo.repo,
state: 'closed',
base: branch,
});
const pr = pullRequests.data.find(pr => pr.merge_commit_sha === context.sha);
const prNumber = pr ? pr.number : null;
// Find the previous release on the branch
const releases = await github.rest.repos.listReleases({
owner: context.repo.owner,
repo: context.repo.repo,
per_page: 100,
});
const branchReleases = releases.data
.filter((release) => {
const regex = new RegExp(`^${branch}-\\d+$`);
return regex.test(release.tag_name) && !release.draft && !release.prerelease;
})
.sort((a, b) => new Date(b.created_at) - new Date(a.created_at));
const previousTag = branchReleases.length > 0 ? branchReleases[0].tag_name : null;
const releaseNotes = [
prNumber
? `Release PR https://github.com/${context.repo.owner}/${context.repo.repo}/pull/${prNumber}.`
: 'Release PR not found.',
previousTag
? `Diff with the previous release https://github.com/${context.repo.owner}/${context.repo.repo}/compare/${previousTag}...${tag}.`
: `No previous release found on branch ${branch}.`,
].join('\n\n');
await github.rest.repos.createRelease({
owner: context.repo.owner,
repo: context.repo.repo,
tag_name: tag,
body: releaseNotes,
});
console.log(`Release for tag ${tag} created successfully.`);
}
- name: Trigger deploy workflow
env:
GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
@@ -1234,20 +1101,43 @@ jobs:
-f deployProxyAuthBroker=true \
-f branch=main \
-f dockerTag=${{needs.tag.outputs.build-tag}}
elif [[ "$GITHUB_REF_NAME" == "release-compute" ]]; then
gh workflow --repo neondatabase/infra run deploy-compute-dev.yml --ref main -f dockerTag=${{needs.tag.outputs.build-tag}}
else
echo "GITHUB_REF_NAME (value '$GITHUB_REF_NAME') is not set to either 'main', 'release', 'release-proxy' or 'release-compute'"
echo "GITHUB_REF_NAME (value '$GITHUB_REF_NAME') is not set to either 'main' or 'release'"
exit 1
fi
- name: Create git tag
if: github.ref_name == 'release' || github.ref_name == 'release-proxy'
uses: actions/github-script@v7
with:
# Retry script for 5XX server errors: https://github.com/actions/github-script#retries
retries: 5
script: |
await github.rest.git.createRef({
owner: context.repo.owner,
repo: context.repo.repo,
ref: "refs/tags/${{ needs.tag.outputs.build-tag }}",
sha: context.sha,
})
# TODO: check how GitHub releases looks for proxy releases and enable it if it's ok
- name: Create GitHub release
if: github.ref_name == 'release'
uses: actions/github-script@v7
with:
# Retry script for 5XX server errors: https://github.com/actions/github-script#retries
retries: 5
script: |
await github.rest.repos.createRelease({
owner: context.repo.owner,
repo: context.repo.repo,
tag_name: "${{ needs.tag.outputs.build-tag }}",
generate_release_notes: true,
})
# The job runs on `release` branch and copies compatibility data and Neon artifact from the last *release PR* to the latest directory
promote-compatibility-data:
needs: [ deploy ]
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: read
# `!failure() && !cancelled()` is required because the workflow transitively depends on the job that can be skipped: `push-to-acr-dev` and `push-to-acr-prod`
if: github.ref_name == 'release' && !failure() && !cancelled()
@@ -1284,12 +1174,6 @@ jobs:
echo "run-id=${run_id}" | tee -a ${GITHUB_OUTPUT}
echo "commit-sha=${last_commit_sha}" | tee -a ${GITHUB_OUTPUT}
- uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 3600
- name: Promote compatibility snapshot and Neon artifact
env:
BUCKET: neon-github-public-dev
@@ -1337,7 +1221,7 @@ jobs:
done
pin-build-tools-image:
needs: [ build-build-tools-image, promote-images-prod, build-and-test-locally ]
needs: [ build-build-tools-image, promote-images, build-and-test-locally ]
if: github.ref_name == 'main'
uses: ./.github/workflows/pin-build-tools-image.yml
with:
@@ -1360,9 +1244,7 @@ jobs:
- build-and-test-locally
- check-codestyle-python
- check-codestyle-rust
- check-dependencies-rust
- files-changed
- promote-images-dev
- promote-images
- test-images
- trigger-custom-extensions-build-and-wait
runs-on: ubuntu-22.04
@@ -1374,11 +1256,4 @@ jobs:
if: |
contains(needs.*.result, 'failure')
|| contains(needs.*.result, 'cancelled')
|| (needs.check-dependencies-rust.result == 'skipped' && needs.files-changed.outputs.check-rust-dependencies == 'true')
|| needs.build-and-test-locally.result == 'skipped'
|| needs.check-codestyle-python.result == 'skipped'
|| needs.check-codestyle-rust.result == 'skipped'
|| needs.files-changed.result == 'skipped'
|| needs.promote-images-dev.result == 'skipped'
|| needs.test-images.result == 'skipped'
|| needs.trigger-custom-extensions-build-and-wait.result == 'skipped'
|| contains(needs.*.result, 'skipped')

View File

@@ -1,133 +0,0 @@
name: Build and Test with Sanitizers
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 1 * * *' # 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: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/base:pinned
outputs:
build-tag: ${{steps.build-tag.outputs.tag}}
steps:
# Need `fetch-depth: 0` to count the number of commits in the branch
- uses: actions/checkout@v4
with:
fetch-depth: 0
- name: Get build tag
run: |
echo run:$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: [ 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 }}
test-cfg: '[{"pg_version":"v17", "sanitizers": "enabled"}]'
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: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
options: --init
steps:
- uses: actions/checkout@v4
- name: Create Allure report
if: ${{ !cancelled() }}
id: create-allure-report
uses: ./.github/actions/allure-report-generate
with:
store-test-results-into-db: true
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
- uses: actions/github-script@v7
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

@@ -1,57 +0,0 @@
name: cargo deny checks
on:
workflow_call:
inputs:
build-tools-image:
required: false
type: string
schedule:
- cron: '0 0 * * *'
jobs:
cargo-deny:
strategy:
matrix:
ref: >-
${{
fromJSON(
github.event_name == 'schedule'
&& '["main","release","release-proxy","release-compute"]'
|| format('["{0}"]', github.sha)
)
}}
runs-on: [self-hosted, small]
container:
image: ${{ inputs.build-tools-image || 'neondatabase/build-tools:pinned' }}
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
options: --init
steps:
- name: Checkout
uses: actions/checkout@v4
with:
ref: ${{ matrix.ref }}
- name: Check rust licenses/bans/advisories/sources
env:
CARGO_DENY_TARGET: >-
${{ github.event_name == 'schedule' && 'advisories' || 'all' }}
run: cargo deny check --hide-inclusion-graph $CARGO_DENY_TARGET
- name: Post to a Slack channel
if: ${{ github.event_name == 'schedule' && failure() }}
uses: slackapi/slack-github-action@v2
with:
method: chat.postMessage
token: ${{ secrets.SLACK_BOT_TOKEN }}
payload: |
channel: ${{ vars.SLACK_CICD_CHANNEL_ID }}
text: |
Periodic cargo-deny on ${{ matrix.ref }}: ${{ job.status }}
<${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}|GitHub Run>
Pinging @oncall-devprod.

View File

@@ -0,0 +1,51 @@
name: Check build-tools image
on:
workflow_call:
outputs:
image-tag:
description: "build-tools image tag"
value: ${{ jobs.check-image.outputs.tag }}
found:
description: "Whether the image is found in the registry"
value: ${{ jobs.check-image.outputs.found }}
defaults:
run:
shell: bash -euo pipefail {0}
# No permission for GITHUB_TOKEN by default; the **minimal required** set of permissions should be granted in each job.
permissions: {}
jobs:
check-image:
runs-on: ubuntu-22.04
outputs:
tag: ${{ steps.get-build-tools-tag.outputs.image-tag }}
found: ${{ steps.check-image.outputs.found }}
steps:
- uses: actions/checkout@v4
- name: Get build-tools image tag for the current commit
id: get-build-tools-tag
env:
IMAGE_TAG: |
${{ hashFiles('build-tools.Dockerfile',
'.github/workflows/check-build-tools-image.yml',
'.github/workflows/build-build-tools-image.yml') }}
run: |
echo "image-tag=${IMAGE_TAG}" | tee -a $GITHUB_OUTPUT
- name: Check if such tag found in the registry
id: check-image
env:
IMAGE_TAG: ${{ steps.get-build-tools-tag.outputs.image-tag }}
run: |
if docker manifest inspect neondatabase/build-tools:${IMAGE_TAG}; then
found=true
else
found=false
fi
echo "found=${found}" | tee -a $GITHUB_OUTPUT

View File

@@ -19,21 +19,15 @@ concurrency:
group: ${{ github.workflow }}
cancel-in-progress: true
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: write
jobs:
regress:
env:
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
DEFAULT_PG_VERSION: 16
TEST_OUTPUT: /tmp/test_output
BUILD_TYPE: remote
strategy:
fail-fast: false
matrix:
pg-version: [16, 17]
AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
runs-on: us-east-2
container:
@@ -46,11 +40,9 @@ jobs:
submodules: true
- name: Patch the test
env:
PG_VERSION: ${{matrix.pg-version}}
run: |
cd "vendor/postgres-v${PG_VERSION}"
patch -p1 < "../../compute/patches/cloud_regress_pg${PG_VERSION}.patch"
cd "vendor/postgres-v${DEFAULT_PG_VERSION}"
patch -p1 < "../../compute/patches/cloud_regress_pg${DEFAULT_PG_VERSION}.patch"
- name: Generate a random password
id: pwgen
@@ -63,9 +55,8 @@ jobs:
- name: Change tests according to the generated password
env:
DBPASS: ${{ steps.pwgen.outputs.DBPASS }}
PG_VERSION: ${{matrix.pg-version}}
run: |
cd vendor/postgres-v"${PG_VERSION}"/src/test/regress
cd vendor/postgres-v"${DEFAULT_PG_VERSION}"/src/test/regress
for fname in sql/*.sql expected/*.out; do
sed -i.bak s/NEON_PASSWORD_PLACEHOLDER/"'${DBPASS}'"/ "${fname}"
done
@@ -81,46 +72,27 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Create a new branch
id: create-branch
uses: ./.github/actions/neon-branch-create
with:
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
project_id: ${{ vars[format('PGREGRESS_PG{0}_PROJECT_ID', matrix.pg-version)] }}
- name: Run the regression tests
uses: ./.github/actions/run-python-test-set
with:
build_type: ${{ env.BUILD_TYPE }}
test_selection: cloud_regress
pg_version: ${{matrix.pg-version}}
pg_version: ${{ env.DEFAULT_PG_VERSION }}
extra_params: -m remote_cluster
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
BENCHMARK_CONNSTR: ${{steps.create-branch.outputs.dsn}}
- name: Delete branch
if: always()
uses: ./.github/actions/neon-branch-delete
with:
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
project_id: ${{ vars[format('PGREGRESS_PG{0}_PROJECT_ID', matrix.pg-version)] }}
branch_id: ${{steps.create-branch.outputs.branch_id}}
BENCHMARK_CONNSTR: ${{ secrets.PG_REGRESS_CONNSTR }}
- name: Create Allure report
id: create-allure-report
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
with:
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@v1
with:
channel-id: ${{ vars.SLACK_ON_CALL_QA_STAGING_STREAM }}
channel-id: "C033QLM5P7D" # on-call-staging-stream
slack-message: |
Periodic pg_regress on staging: ${{ job.status }}
<${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}|GitHub Run>

View File

@@ -1,4 +1,4 @@
name: benchmarking ingest
name: Benchmarking
on:
# uncomment to run on push for debugging your PR
@@ -13,7 +13,7 @@ on:
# │ │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
- cron: '0 9 * * *' # run once a day, timezone is utc
workflow_dispatch: # adds ability to run this manually
defaults:
run:
shell: bash -euxo pipefail {0}
@@ -26,26 +26,8 @@ concurrency:
jobs:
ingest:
strategy:
fail-fast: false # allow other variants to continue even if one fails
matrix:
include:
- target_project: new_empty_project_stripe_size_2048
stripe_size: 2048 # 16 MiB
postgres_version: 16
- target_project: new_empty_project_stripe_size_32768
stripe_size: 32768 # 256 MiB # note that this is different from null because using null will shard_split the project only if it reaches the threshold
# while here it is sharded from the beginning with a shard size of 256 MiB
postgres_version: 16
- target_project: new_empty_project
stripe_size: null # run with neon defaults which will shard split only when reaching the threshold
postgres_version: 16
- target_project: new_empty_project
stripe_size: null # run with neon defaults which will shard split only when reaching the threshold
postgres_version: 17
- target_project: large_existing_project
stripe_size: null # cannot re-shared or choose different stripe size for existing, already sharded project
postgres_version: 16
max-parallel: 1 # we want to run each stripe size sequentially to be able to compare the results
target_project: [new_empty_project, large_existing_project]
permissions:
contents: write
statuses: write
@@ -73,7 +55,7 @@ jobs:
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 18000 # 5 hours is currently max associated with IAM role
role-duration-seconds: 18000 # 5 hours is currently max associated with IAM role
- name: Download Neon artifact
uses: ./.github/actions/download
@@ -81,32 +63,29 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Create Neon Project
if: ${{ startsWith(matrix.target_project, 'new_empty_project') }}
if: ${{ matrix.target_project == 'new_empty_project' }}
id: create-neon-project-ingest-target
uses: ./.github/actions/neon-project-create
with:
region_id: aws-us-east-2
postgres_version: ${{ matrix.postgres_version }}
postgres_version: 16
compute_units: '[7, 7]' # we want to test large compute here to avoid compute-side bottleneck
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
shard_split_project: ${{ matrix.stripe_size != null && 'true' || 'false' }}
admin_api_key: ${{ secrets.NEON_STAGING_ADMIN_API_KEY }}
shard_count: 8
stripe_size: ${{ matrix.stripe_size }}
- name: Initialize Neon project
if: ${{ startsWith(matrix.target_project, 'new_empty_project') }}
- name: Initialize Neon project and retrieve current backpressure seconds
if: ${{ matrix.target_project == 'new_empty_project' }}
env:
BENCHMARK_INGEST_TARGET_CONNSTR: ${{ steps.create-neon-project-ingest-target.outputs.dsn }}
NEW_PROJECT_CONNSTR: ${{ steps.create-neon-project-ingest-target.outputs.dsn }}
NEW_PROJECT_ID: ${{ steps.create-neon-project-ingest-target.outputs.project_id }}
run: |
echo "Initializing Neon project with project_id: ${NEW_PROJECT_ID}"
export LD_LIBRARY_PATH=${PG_16_LIB_PATH}
${PSQL} "${BENCHMARK_INGEST_TARGET_CONNSTR}" -c "CREATE EXTENSION IF NOT EXISTS neon; CREATE EXTENSION IF NOT EXISTS neon_utils;"
echo "BENCHMARK_INGEST_TARGET_CONNSTR=${BENCHMARK_INGEST_TARGET_CONNSTR}" >> $GITHUB_ENV
${PSQL} "${NEW_PROJECT_CONNSTR}" -c "CREATE EXTENSION IF NOT EXISTS neon; CREATE EXTENSION IF NOT EXISTS neon_utils;"
BACKPRESSURE_TIME_BEFORE_INGEST=$(${PSQL} "${NEW_PROJECT_CONNSTR}" -t -c "select backpressure_throttling_time()/1000000;")
echo "BACKPRESSURE_TIME_BEFORE_INGEST=${BACKPRESSURE_TIME_BEFORE_INGEST}" >> $GITHUB_ENV
echo "NEW_PROJECT_CONNSTR=${NEW_PROJECT_CONNSTR}" >> $GITHUB_ENV
- name: Create Neon Branch for large tenant
if: ${{ matrix.target_project == 'large_existing_project' }}
@@ -116,58 +95,269 @@ jobs:
project_id: ${{ vars.BENCHMARK_INGEST_TARGET_PROJECTID }}
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
- name: Initialize Neon project
- name: Initialize Neon project and retrieve current backpressure seconds
if: ${{ matrix.target_project == 'large_existing_project' }}
env:
BENCHMARK_INGEST_TARGET_CONNSTR: ${{ steps.create-neon-branch-ingest-target.outputs.dsn }}
NEW_PROJECT_CONNSTR: ${{ steps.create-neon-branch-ingest-target.outputs.dsn }}
NEW_BRANCH_ID: ${{ steps.create-neon-branch-ingest-target.outputs.branch_id }}
run: |
echo "Initializing Neon branch with branch_id: ${NEW_BRANCH_ID}"
export LD_LIBRARY_PATH=${PG_16_LIB_PATH}
# Extract the part before the database name
base_connstr="${BENCHMARK_INGEST_TARGET_CONNSTR%/*}"
base_connstr="${NEW_PROJECT_CONNSTR%/*}"
# Extract the query parameters (if any) after the database name
query_params="${BENCHMARK_INGEST_TARGET_CONNSTR#*\?}"
query_params="${NEW_PROJECT_CONNSTR#*\?}"
# Reconstruct the new connection string
if [ "$query_params" != "$BENCHMARK_INGEST_TARGET_CONNSTR" ]; then
if [ "$query_params" != "$NEW_PROJECT_CONNSTR" ]; then
new_connstr="${base_connstr}/neondb?${query_params}"
else
new_connstr="${base_connstr}/neondb"
fi
${PSQL} "${new_connstr}" -c "drop database ludicrous;"
${PSQL} "${new_connstr}" -c "CREATE DATABASE ludicrous;"
if [ "$query_params" != "$BENCHMARK_INGEST_TARGET_CONNSTR" ]; then
BENCHMARK_INGEST_TARGET_CONNSTR="${base_connstr}/ludicrous?${query_params}"
if [ "$query_params" != "$NEW_PROJECT_CONNSTR" ]; then
NEW_PROJECT_CONNSTR="${base_connstr}/ludicrous?${query_params}"
else
BENCHMARK_INGEST_TARGET_CONNSTR="${base_connstr}/ludicrous"
NEW_PROJECT_CONNSTR="${base_connstr}/ludicrous"
fi
${PSQL} "${BENCHMARK_INGEST_TARGET_CONNSTR}" -c "CREATE EXTENSION IF NOT EXISTS neon; CREATE EXTENSION IF NOT EXISTS neon_utils;"
echo "BENCHMARK_INGEST_TARGET_CONNSTR=${BENCHMARK_INGEST_TARGET_CONNSTR}" >> $GITHUB_ENV
${PSQL} "${NEW_PROJECT_CONNSTR}" -c "CREATE EXTENSION IF NOT EXISTS neon; CREATE EXTENSION IF NOT EXISTS neon_utils;"
BACKPRESSURE_TIME_BEFORE_INGEST=$(${PSQL} "${NEW_PROJECT_CONNSTR}" -t -c "select backpressure_throttling_time()/1000000;")
echo "BACKPRESSURE_TIME_BEFORE_INGEST=${BACKPRESSURE_TIME_BEFORE_INGEST}" >> $GITHUB_ENV
echo "NEW_PROJECT_CONNSTR=${NEW_PROJECT_CONNSTR}" >> $GITHUB_ENV
- name: Create pgcopydb filter file
run: |
cat << EOF > /tmp/pgcopydb_filter.txt
[include-only-table]
public.events
public.emails
public.email_transmissions
public.payments
public.editions
public.edition_modules
public.sp_content
public.email_broadcasts
public.user_collections
public.devices
public.user_accounts
public.lessons
public.lesson_users
public.payment_methods
public.orders
public.course_emails
public.modules
public.users
public.module_users
public.courses
public.payment_gateway_keys
public.accounts
public.roles
public.payment_gateways
public.management
public.event_names
EOF
- name: Invoke pgcopydb
uses: ./.github/actions/run-python-test-set
with:
build_type: remote
test_selection: performance/test_perf_ingest_using_pgcopydb.py
run_in_parallel: false
extra_params: -s -m remote_cluster --timeout 86400 -k test_ingest_performance_using_pgcopydb
pg_version: v${{ matrix.postgres_version }}
save_perf_report: true
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
BENCHMARK_INGEST_SOURCE_CONNSTR: ${{ secrets.BENCHMARK_INGEST_SOURCE_CONNSTR }}
TARGET_PROJECT_TYPE: ${{ matrix.target_project }}
# we report PLATFORM in zenbenchmark NeonBenchmarker perf database and want to distinguish between new project and large tenant
PLATFORM: "${{ matrix.target_project }}-us-east-2-staging"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
BENCHMARK_INGEST_SOURCE_CONNSTR: ${{ secrets.BENCHMARK_INGEST_SOURCE_CONNSTR }}
run: |
export LD_LIBRARY_PATH=${PGCOPYDB_LIB_PATH}:${PG_16_LIB_PATH}
export PGCOPYDB_SOURCE_PGURI="${BENCHMARK_INGEST_SOURCE_CONNSTR}"
export PGCOPYDB_TARGET_PGURI="${NEW_PROJECT_CONNSTR}"
export PGOPTIONS="-c maintenance_work_mem=8388608 -c max_parallel_maintenance_workers=7"
${PG_CONFIG} --bindir
${PGCOPYDB} --version
${PGCOPYDB} clone --skip-vacuum --no-owner --no-acl --skip-db-properties --table-jobs 4 \
--index-jobs 4 --restore-jobs 4 --split-tables-larger-than 10GB --skip-extensions \
--use-copy-binary --filters /tmp/pgcopydb_filter.txt 2>&1 | tee /tmp/pgcopydb_${{ matrix.target_project }}.log
- name: show tables sizes after ingest
# create dummy pgcopydb log to test parsing
# - name: create dummy log for parser test
# run: |
# cat << EOF > /tmp/pgcopydb_${{ matrix.target_project }}.log
# 2024-11-04 18:00:53.433 500861 INFO main.c:136 Running pgcopydb version 0.17.10.g8361a93 from "/usr/lib/postgresql/17/bin/pgcopydb"
# 2024-11-04 18:00:53.434 500861 INFO cli_common.c:1225 [SOURCE] Copying database from "postgres://neondb_owner@ep-bitter-shape-w2c1ir0a.us-east-2.aws.neon.build/neondb?sslmode=require&keepalives=1&keepalives_idle=10&keepalives_interval=10&keepalives_count=60"
# 2024-11-04 18:00:53.434 500861 INFO cli_common.c:1226 [TARGET] Copying database into "postgres://neondb_owner@ep-icy-union-w25qd5pj.us-east-2.aws.neon.build/ludicrous?sslmode=require&keepalives=1&keepalives_idle=10&keepalives_interval=10&keepalives_count=60"
# 2024-11-04 18:00:53.442 500861 INFO copydb.c:105 Using work dir "/tmp/pgcopydb"
# 2024-11-04 18:00:53.541 500861 INFO snapshot.c:107 Exported snapshot "00000008-00000033-1" from the source database
# 2024-11-04 18:00:53.556 500865 INFO cli_clone_follow.c:543 STEP 1: fetch source database tables, indexes, and sequences
# 2024-11-04 18:00:54.570 500865 INFO copydb_schema.c:716 Splitting source candidate tables larger than 10 GB
# 2024-11-04 18:00:54.570 500865 INFO copydb_schema.c:829 Table public.events is 96 GB large which is larger than --split-tables-larger-than 10 GB, and does not have a unique column of type integer: splitting by CTID
# 2024-11-04 18:01:05.538 500865 INFO copydb_schema.c:905 Table public.events is 96 GB large, 10 COPY processes will be used, partitioning on ctid.
# 2024-11-04 18:01:05.564 500865 INFO copydb_schema.c:905 Table public.email_transmissions is 27 GB large, 4 COPY processes will be used, partitioning on id.
# 2024-11-04 18:01:05.584 500865 INFO copydb_schema.c:905 Table public.lessons is 25 GB large, 4 COPY processes will be used, partitioning on id.
# 2024-11-04 18:01:05.605 500865 INFO copydb_schema.c:905 Table public.lesson_users is 16 GB large, 3 COPY processes will be used, partitioning on id.
# 2024-11-04 18:01:05.605 500865 INFO copydb_schema.c:761 Fetched information for 26 tables (including 4 tables split in 21 partitions total), with an estimated total of 907 million tuples and 175 GB on-disk
# 2024-11-04 18:01:05.687 500865 INFO copydb_schema.c:968 Fetched information for 57 indexes (supporting 25 constraints)
# 2024-11-04 18:01:05.753 500865 INFO sequences.c:78 Fetching information for 24 sequences
# 2024-11-04 18:01:05.903 500865 INFO copydb_schema.c:1122 Fetched information for 4 extensions
# 2024-11-04 18:01:06.178 500865 INFO copydb_schema.c:1538 Found 0 indexes (supporting 0 constraints) in the target database
# 2024-11-04 18:01:06.184 500865 INFO cli_clone_follow.c:584 STEP 2: dump the source database schema (pre/post data)
# 2024-11-04 18:01:06.186 500865 INFO pgcmd.c:468 /usr/lib/postgresql/16/bin/pg_dump -Fc --snapshot 00000008-00000033-1 --section=pre-data --section=post-data --file /tmp/pgcopydb/schema/schema.dump 'postgres://neondb_owner@ep-bitter-shape-w2c1ir0a.us-east-2.aws.neon.build/neondb?sslmode=require&keepalives=1&keepalives_idle=10&keepalives_interval=10&keepalives_count=60'
# 2024-11-04 18:01:06.952 500865 INFO cli_clone_follow.c:592 STEP 3: restore the pre-data section to the target database
# 2024-11-04 18:01:07.004 500865 INFO pgcmd.c:1001 /usr/lib/postgresql/16/bin/pg_restore --dbname 'postgres://neondb_owner@ep-icy-union-w25qd5pj.us-east-2.aws.neon.build/ludicrous?sslmode=require&keepalives=1&keepalives_idle=10&keepalives_interval=10&keepalives_count=60' --section pre-data --jobs 4 --no-owner --no-acl --use-list /tmp/pgcopydb/schema/pre-filtered.list /tmp/pgcopydb/schema/schema.dump
# 2024-11-04 18:01:07.438 500874 INFO table-data.c:656 STEP 4: starting 4 table-data COPY processes
# 2024-11-04 18:01:07.451 500877 INFO vacuum.c:139 STEP 8: skipping VACUUM jobs per --skip-vacuum
# 2024-11-04 18:01:07.457 500875 INFO indexes.c:182 STEP 6: starting 4 CREATE INDEX processes
# 2024-11-04 18:01:07.457 500875 INFO indexes.c:183 STEP 7: constraints are built by the CREATE INDEX processes
# 2024-11-04 18:01:07.507 500865 INFO blobs.c:74 Skipping large objects: none found.
# 2024-11-04 18:01:07.509 500865 INFO sequences.c:194 STEP 9: reset sequences values
# 2024-11-04 18:01:07.510 500886 INFO sequences.c:290 Set sequences values on the target database
# 2024-11-04 20:49:00.587 500865 INFO cli_clone_follow.c:608 STEP 10: restore the post-data section to the target database
# 2024-11-04 20:49:00.600 500865 INFO pgcmd.c:1001 /usr/lib/postgresql/16/bin/pg_restore --dbname 'postgres://neondb_owner@ep-icy-union-w25qd5pj.us-east-2.aws.neon.build/ludicrous?sslmode=require&keepalives=1&keepalives_idle=10&keepalives_interval=10&keepalives_count=60' --section post-data --jobs 4 --no-owner --no-acl --use-list /tmp/pgcopydb/schema/post-filtered.list /tmp/pgcopydb/schema/schema.dump
# 2024-11-05 10:50:58.508 500865 INFO cli_clone_follow.c:639 All step are now done, 16h49m elapsed
# 2024-11-05 10:50:58.508 500865 INFO summary.c:3155 Printing summary for 26 tables and 57 indexes
# OID | Schema | Name | Parts | copy duration | transmitted bytes | indexes | create index duration
# ------+--------+----------------------+-------+---------------+-------------------+---------+----------------------
# 24654 | public | events | 10 | 1d11h | 878 GB | 1 | 1h41m
# 24623 | public | email_transmissions | 4 | 4h46m | 99 GB | 3 | 2h04m
# 24665 | public | lessons | 4 | 4h42m | 161 GB | 4 | 1m11s
# 24661 | public | lesson_users | 3 | 2h46m | 49 GB | 3 | 39m35s
# 24631 | public | emails | 1 | 34m07s | 10 GB | 2 | 17s
# 24739 | public | payments | 1 | 5m47s | 1848 MB | 4 | 4m40s
# 24681 | public | module_users | 1 | 4m57s | 1610 MB | 3 | 1m50s
# 24694 | public | orders | 1 | 2m50s | 835 MB | 3 | 1m05s
# 24597 | public | devices | 1 | 1m45s | 498 MB | 2 | 40s
# 24723 | public | payment_methods | 1 | 1m24s | 548 MB | 2 | 31s
# 24765 | public | user_collections | 1 | 2m17s | 1005 MB | 2 | 968ms
# 24774 | public | users | 1 | 52s | 291 MB | 4 | 27s
# 24760 | public | user_accounts | 1 | 16s | 172 MB | 3 | 16s
# 24606 | public | edition_modules | 1 | 8s983 | 46 MB | 3 | 4s749
# 24583 | public | course_emails | 1 | 8s526 | 26 MB | 2 | 996ms
# 24685 | public | modules | 1 | 1s592 | 21 MB | 3 | 1s696
# 24610 | public | editions | 1 | 2s199 | 7483 kB | 2 | 1s032
# 24755 | public | sp_content | 1 | 1s555 | 4177 kB | 0 | 0ms
# 24619 | public | email_broadcasts | 1 | 744ms | 2645 kB | 2 | 677ms
# 24590 | public | courses | 1 | 387ms | 1540 kB | 2 | 367ms
# 24704 | public | payment_gateway_keys | 1 | 1s972 | 164 kB | 2 | 27ms
# 24576 | public | accounts | 1 | 58ms | 24 kB | 1 | 14ms
# 24647 | public | event_names | 1 | 32ms | 397 B | 1 | 8ms
# 24716 | public | payment_gateways | 1 | 1s675 | 117 B | 1 | 11ms
# 24748 | public | roles | 1 | 71ms | 173 B | 1 | 8ms
# 24676 | public | management | 1 | 33ms | 40 B | 1 | 19ms
# Step Connection Duration Transfer Concurrency
# -------------------------------------------------- ---------- ---------- ---------- ------------
# Catalog Queries (table ordering, filtering, etc) source 12s 1
# Dump Schema source 765ms 1
# Prepare Schema target 466ms 1
# COPY, INDEX, CONSTRAINTS, VACUUM (wall clock) both 2h47m 12
# COPY (cumulative) both 7h46m 1225 GB 4
# CREATE INDEX (cumulative) target 4h36m 4
# CONSTRAINTS (cumulative) target 8s493 4
# VACUUM (cumulative) target 0ms 4
# Reset Sequences both 60ms 1
# Large Objects (cumulative) (null) 0ms 0
# Finalize Schema both 14h01m 4
# -------------------------------------------------- ---------- ---------- ---------- ------------
# Total Wall Clock Duration both 16h49m 20
# EOF
- name: show tables sizes and retrieve current backpressure seconds
run: |
export LD_LIBRARY_PATH=${PG_16_LIB_PATH}
${PSQL} "${BENCHMARK_INGEST_TARGET_CONNSTR}" -c "\dt+"
${PSQL} "${NEW_PROJECT_CONNSTR}" -c "\dt+"
BACKPRESSURE_TIME_AFTER_INGEST=$(${PSQL} "${NEW_PROJECT_CONNSTR}" -t -c "select backpressure_throttling_time()/1000000;")
echo "BACKPRESSURE_TIME_AFTER_INGEST=${BACKPRESSURE_TIME_AFTER_INGEST}" >> $GITHUB_ENV
- name: Parse pgcopydb log and report performance metrics
env:
PERF_TEST_RESULT_CONNSTR: ${{ secrets.PERF_TEST_RESULT_CONNSTR }}
run: |
export LD_LIBRARY_PATH=${PG_16_LIB_PATH}
# Define the log file path
LOG_FILE="/tmp/pgcopydb_${{ matrix.target_project }}.log"
# Get the current git commit hash
git config --global --add safe.directory /__w/neon/neon
COMMIT_HASH=$(git rev-parse --short HEAD)
# Define the platform and test suite
PLATFORM="pg16-${{ matrix.target_project }}-us-east-2-staging"
SUIT="pgcopydb_ingest_bench"
# Function to convert time (e.g., "2h47m", "4h36m", "118ms", "8s493") to seconds
convert_to_seconds() {
local duration=$1
local total_seconds=0
# Check for hours (h)
if [[ "$duration" =~ ([0-9]+)h ]]; then
total_seconds=$((total_seconds + ${BASH_REMATCH[1]#0} * 3600))
fi
# Check for seconds (s)
if [[ "$duration" =~ ([0-9]+)s ]]; then
total_seconds=$((total_seconds + ${BASH_REMATCH[1]#0}))
fi
# Check for milliseconds (ms) (if applicable)
if [[ "$duration" =~ ([0-9]+)ms ]]; then
total_seconds=$((total_seconds + ${BASH_REMATCH[1]#0} / 1000))
duration=${duration/${BASH_REMATCH[0]}/} # need to remove it to avoid double counting with m
fi
# Check for minutes (m) - must be checked after ms because m is contained in ms
if [[ "$duration" =~ ([0-9]+)m ]]; then
total_seconds=$((total_seconds + ${BASH_REMATCH[1]#0} * 60))
fi
echo $total_seconds
}
# Calculate the backpressure difference in seconds
BACKPRESSURE_TIME_DIFF=$(awk "BEGIN {print $BACKPRESSURE_TIME_AFTER_INGEST - $BACKPRESSURE_TIME_BEFORE_INGEST}")
# Insert the backpressure time difference into the performance database
if [ -n "$BACKPRESSURE_TIME_DIFF" ]; then
PSQL_CMD="${PSQL} \"${PERF_TEST_RESULT_CONNSTR}\" -c \"
INSERT INTO public.perf_test_results (suit, revision, platform, metric_name, metric_value, metric_unit, metric_report_type, recorded_at_timestamp)
VALUES ('${SUIT}', '${COMMIT_HASH}', '${PLATFORM}', 'backpressure_time', ${BACKPRESSURE_TIME_DIFF}, 'seconds', 'lower_is_better', now());
\""
echo "Inserting backpressure time difference: ${BACKPRESSURE_TIME_DIFF} seconds"
eval $PSQL_CMD
fi
# Extract and process log lines
while IFS= read -r line; do
METRIC_NAME=""
# Match each desired line and extract the relevant information
if [[ "$line" =~ COPY,\ INDEX,\ CONSTRAINTS,\ VACUUM.* ]]; then
METRIC_NAME="COPY, INDEX, CONSTRAINTS, VACUUM (wall clock)"
elif [[ "$line" =~ COPY\ \(cumulative\).* ]]; then
METRIC_NAME="COPY (cumulative)"
elif [[ "$line" =~ CREATE\ INDEX\ \(cumulative\).* ]]; then
METRIC_NAME="CREATE INDEX (cumulative)"
elif [[ "$line" =~ CONSTRAINTS\ \(cumulative\).* ]]; then
METRIC_NAME="CONSTRAINTS (cumulative)"
elif [[ "$line" =~ Finalize\ Schema.* ]]; then
METRIC_NAME="Finalize Schema"
elif [[ "$line" =~ Total\ Wall\ Clock\ Duration.* ]]; then
METRIC_NAME="Total Wall Clock Duration"
fi
# If a metric was matched, insert it into the performance database
if [ -n "$METRIC_NAME" ]; then
DURATION=$(echo "$line" | grep -oP '\d+h\d+m|\d+s|\d+ms|\d{1,2}h\d{1,2}m|\d+\.\d+s' | head -n 1)
METRIC_VALUE=$(convert_to_seconds "$DURATION")
PSQL_CMD="${PSQL} \"${PERF_TEST_RESULT_CONNSTR}\" -c \"
INSERT INTO public.perf_test_results (suit, revision, platform, metric_name, metric_value, metric_unit, metric_report_type, recorded_at_timestamp)
VALUES ('${SUIT}', '${COMMIT_HASH}', '${PLATFORM}', '${METRIC_NAME}', ${METRIC_VALUE}, 'seconds', 'lower_is_better', now());
\""
echo "Inserting ${METRIC_NAME} with value ${METRIC_VALUE} seconds"
eval $PSQL_CMD
fi
done < "$LOG_FILE"
- name: Delete Neon Project
if: ${{ always() && startsWith(matrix.target_project, 'new_empty_project') }}
if: ${{ always() && matrix.target_project == 'new_empty_project' }}
uses: ./.github/actions/neon-project-delete
with:
project_id: ${{ steps.create-neon-project-ingest-target.outputs.project_id }}

View File

@@ -26,20 +26,30 @@ jobs:
with:
github-event-name: ${{ github.event_name}}
build-build-tools-image:
check-build-tools-image:
needs: [ check-permissions ]
uses: ./.github/workflows/check-build-tools-image.yml
build-build-tools-image:
needs: [ check-build-tools-image ]
uses: ./.github/workflows/build-build-tools-image.yml
with:
image-tag: ${{ needs.check-build-tools-image.outputs.image-tag }}
secrets: inherit
files-changed:
name: Detect what files changed
runs-on: ubuntu-22.04
timeout-minutes: 3
outputs:
v17: ${{ steps.files_changed.outputs.v17 }}
postgres_changes: ${{ steps.postgres_changes.outputs.changes }}
rebuild_rust_code: ${{ steps.files_changed.outputs.rust_code }}
rebuild_everything: ${{ steps.files_changed.outputs.rebuild_neon_extra || steps.files_changed.outputs.rebuild_macos }}
check-macos-build:
needs: [ check-permissions ]
if: |
contains(github.event.pull_request.labels.*.name, 'run-extra-build-macos') ||
contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
github.ref_name == 'main'
timeout-minutes: 90
runs-on: macos-14
env:
# Use release build only, to have less debug info around
# Hence keeping target/ (and general cache size) smaller
BUILD_TYPE: release
steps:
- name: Checkout
@@ -47,45 +57,102 @@ jobs:
with:
submodules: true
- name: Check for Postgres changes
uses: dorny/paths-filter@1441771bbfdd59dcd748680ee64ebd8faab1a242 #v3
id: files_changed
- name: Install macOS postgres dependencies
run: brew install flex bison openssl protobuf icu4c pkg-config
- name: Set pg 14 revision for caching
id: pg_v14_rev
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v14) >> $GITHUB_OUTPUT
- name: Set pg 15 revision for caching
id: pg_v15_rev
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v15) >> $GITHUB_OUTPUT
- name: Set pg 16 revision for caching
id: pg_v16_rev
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v16) >> $GITHUB_OUTPUT
- name: Set pg 17 revision for caching
id: pg_v17_rev
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v17) >> $GITHUB_OUTPUT
- name: Cache postgres v14 build
id: cache_pg_14
uses: actions/cache@v4
with:
token: ${{ github.token }}
filters: .github/file-filters.yaml
base: ${{ github.event_name != 'pull_request' && (github.event.merge_group.base_ref || github.ref_name) || '' }}
ref: ${{ github.event_name != 'pull_request' && (github.event.merge_group.head_ref || github.ref) || '' }}
path: pg_install/v14
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-${{ steps.pg_v14_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Filter out only v-string for build matrix
id: postgres_changes
- name: Cache postgres v15 build
id: cache_pg_15
uses: actions/cache@v4
with:
path: pg_install/v15
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-${{ steps.pg_v15_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Cache postgres v16 build
id: cache_pg_16
uses: actions/cache@v4
with:
path: pg_install/v16
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-${{ steps.pg_v16_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Cache postgres v17 build
id: cache_pg_17
uses: actions/cache@v4
with:
path: pg_install/v17
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-${{ steps.pg_v17_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Set extra env for macOS
run: |
v_strings_only_as_json_array=$(echo ${{ steps.files_changed.outputs.chnages }} | jq '.[]|select(test("v\\d+"))' | jq --slurp -c)
echo "changes=${v_strings_only_as_json_array}" | tee -a "${GITHUB_OUTPUT}"
echo 'LDFLAGS=-L/usr/local/opt/openssl@3/lib' >> $GITHUB_ENV
echo 'CPPFLAGS=-I/usr/local/opt/openssl@3/include' >> $GITHUB_ENV
check-macos-build:
needs: [ check-permissions, files-changed ]
if: |
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'
uses: ./.github/workflows/build-macos.yml
with:
pg_versions: ${{ needs.files-changed.outputs.postgres_changes }}
rebuild_rust_code: ${{ needs.files-changed.outputs.rebuild_rust_code }}
rebuild_everything: ${{ fromJson(needs.files-changed.outputs.rebuild_everything) }}
- name: Cache cargo deps
uses: actions/cache@v4
with:
path: |
~/.cargo/registry
!~/.cargo/registry/src
~/.cargo/git
target
key: v1-${{ runner.os }}-${{ runner.arch }}-cargo-${{ hashFiles('./Cargo.lock') }}-${{ hashFiles('./rust-toolchain.toml') }}-rust
- name: Build postgres v14
if: steps.cache_pg_14.outputs.cache-hit != 'true'
run: make postgres-v14 -j$(sysctl -n hw.ncpu)
- name: Build postgres v15
if: steps.cache_pg_15.outputs.cache-hit != 'true'
run: make postgres-v15 -j$(sysctl -n hw.ncpu)
- name: Build postgres v16
if: steps.cache_pg_16.outputs.cache-hit != 'true'
run: make postgres-v16 -j$(sysctl -n hw.ncpu)
- name: Build postgres v17
if: steps.cache_pg_17.outputs.cache-hit != 'true'
run: make postgres-v17 -j$(sysctl -n hw.ncpu)
- name: Build neon extensions
run: make neon-pg-ext -j$(sysctl -n hw.ncpu)
- name: Build walproposer-lib
run: make walproposer-lib -j$(sysctl -n hw.ncpu)
- name: Run cargo build
run: PQ_LIB_DIR=$(pwd)/pg_install/v16/lib cargo build --all --release
- name: Check that no warnings are produced
run: ./run_clippy.sh
gather-rust-build-stats:
needs: [ check-permissions, build-build-tools-image, files-changed ]
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: write
needs: [ check-permissions, build-build-tools-image ]
if: |
(needs.files-changed.outputs.v17 == 'true' || needs.files-changed.outputs.rebuild_everything == 'true') && (
contains(github.event.pull_request.labels.*.name, 'run-extra-build-stats') ||
contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
github.ref_name == 'main'
)
contains(github.event.pull_request.labels.*.name, 'run-extra-build-stats') ||
contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
github.ref_name == 'main'
runs-on: [ self-hosted, large ]
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
@@ -114,20 +181,15 @@ jobs:
run: make walproposer-lib -j$(nproc)
- name: Produce the build stats
run: cargo build --all --release --timings -j$(nproc)
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 3600
run: PQ_LIB_DIR=$(pwd)/pg_install/v17/lib cargo build --all --release --timings -j$(nproc)
- name: Upload the build stats
id: upload-stats
env:
BUCKET: neon-github-public-dev
SHA: ${{ github.event.pull_request.head.sha || github.sha }}
AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
run: |
REPORT_URL=https://${BUCKET}.s3.amazonaws.com/build-stats/${SHA}/${GITHUB_RUN_ID}/cargo-timing.html
aws s3 cp --only-show-errors ./target/cargo-timings/cargo-timing.html "s3://${BUCKET}/build-stats/${SHA}/${GITHUB_RUN_ID}/"

View File

@@ -27,14 +27,9 @@ concurrency:
jobs:
trigger_bench_on_ec2_machine_in_eu_central_1:
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: write
pull-requests: write
runs-on: [ self-hosted, small ]
container:
image: neondatabase/build-tools:pinned-bookworm
image: neondatabase/build-tools:pinned
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
@@ -43,6 +38,8 @@ jobs:
env:
API_KEY: ${{ secrets.PERIODIC_PAGEBENCH_EC2_RUNNER_API_KEY }}
RUN_ID: ${{ github.run_id }}
AWS_ACCESS_KEY_ID: ${{ secrets.AWS_EC2_US_TEST_RUNNER_ACCESS_KEY_ID }}
AWS_SECRET_ACCESS_KEY : ${{ secrets.AWS_EC2_US_TEST_RUNNER_ACCESS_KEY_SECRET }}
AWS_DEFAULT_REGION : "eu-central-1"
AWS_INSTANCE_ID : "i-02a59a3bf86bc7e74"
steps:
@@ -53,13 +50,6 @@ jobs:
- name: Show my own (github runner) external IP address - usefull for IP allowlisting
run: curl https://ifconfig.me
- name: Assume AWS OIDC role that allows to manage (start/stop/describe... EC machine)
uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_MANAGE_BENCHMARK_EC2_VMS_ARN }}
role-duration-seconds: 3600
- name: Start EC2 instance and wait for the instance to boot up
run: |
aws ec2 start-instances --instance-ids $AWS_INSTANCE_ID
@@ -82,7 +72,7 @@ jobs:
echo "COMMIT_HASH=$INPUT_COMMIT_HASH" >> $GITHUB_ENV
fi
- name: Start Bench with run_id
- name: Start Bench with run_id
run: |
curl -k -X 'POST' \
"${EC2_MACHINE_URL_US}/start_test/${GITHUB_RUN_ID}" \
@@ -126,7 +116,7 @@ jobs:
-H 'accept: application/gzip' \
-H "Authorization: Bearer $API_KEY" \
--output "test_log_${GITHUB_RUN_ID}.gz"
- name: Unzip Test Log and Print it into this job's log
if: always() && steps.poll_step.outputs.too_many_runs != 'true'
run: |
@@ -134,22 +124,23 @@ jobs:
cat "test_log_${GITHUB_RUN_ID}"
- name: Create Allure report
env:
AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
with:
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@v1
with:
channel-id: "C06KHQVQ7U3" # on-call-qa-staging-stream
channel-id: "C033QLM5P7D" # dev-staging-stream
slack-message: "Periodic pagebench testing on dedicated hardware: ${{ job.status }}\n${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}"
env:
SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
- name: Cleanup Test Resources
if: always()
if: always()
run: |
curl -k -X 'POST' \
"${EC2_MACHINE_URL_US}/cleanup_test/${GITHUB_RUN_ID}" \
@@ -157,14 +148,6 @@ jobs:
-H "Authorization: Bearer $API_KEY" \
-d ''
- name: Assume AWS OIDC role that allows to manage (start/stop/describe... EC machine)
if: always() && steps.poll_step.outputs.too_many_runs != 'true'
uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_MANAGE_BENCHMARK_EC2_VMS_ARN }}
role-duration-seconds: 3600
- name: Stop EC2 instance and wait for the instance to be stopped
if: always() && steps.poll_step.outputs.too_many_runs != 'true'
run: |

View File

@@ -12,8 +12,8 @@ on:
pull_request:
paths:
- '.github/workflows/pg-clients.yml'
- 'test_runner/pg_clients/**/*.py'
- 'test_runner/logical_repl/**/*.py'
- 'test_runner/pg_clients/**'
- 'test_runner/logical_repl/**'
- 'poetry.lock'
workflow_dispatch:
@@ -25,13 +25,11 @@ defaults:
run:
shell: bash -euxo pipefail {0}
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write # require for posting a status update
env:
DEFAULT_PG_VERSION: 16
PLATFORM: neon-captest-new
AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
AWS_DEFAULT_REGION: eu-central-1
jobs:
@@ -41,9 +39,15 @@ jobs:
with:
github-event-name: ${{ github.event_name }}
build-build-tools-image:
check-build-tools-image:
needs: [ check-permissions ]
uses: ./.github/workflows/check-build-tools-image.yml
build-build-tools-image:
needs: [ check-build-tools-image ]
uses: ./.github/workflows/build-build-tools-image.yml
with:
image-tag: ${{ needs.check-build-tools-image.outputs.image-tag }}
secrets: inherit
test-logical-replication:
@@ -96,7 +100,6 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Create Neon Project
id: create-neon-project
@@ -104,8 +107,6 @@ jobs:
with:
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
postgres_version: ${{ env.DEFAULT_PG_VERSION }}
project_settings: >-
{"enable_logical_replication": true}
- name: Run tests
uses: ./.github/actions/run-python-test-set
@@ -115,7 +116,6 @@ jobs:
run_in_parallel: false
extra_params: -m remote_cluster
pg_version: ${{ env.DEFAULT_PG_VERSION }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
BENCHMARK_CONNSTR: ${{ steps.create-neon-project.outputs.dsn }}
@@ -132,7 +132,6 @@ jobs:
uses: ./.github/actions/allure-report-generate
with:
store-test-results-into-db: true
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
@@ -166,7 +165,6 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Create Neon Project
id: create-neon-project
@@ -183,7 +181,6 @@ jobs:
run_in_parallel: false
extra_params: -m remote_cluster
pg_version: ${{ env.DEFAULT_PG_VERSION }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
BENCHMARK_CONNSTR: ${{ steps.create-neon-project.outputs.dsn }}
@@ -200,7 +197,6 @@ jobs:
uses: ./.github/actions/allure-report-generate
with:
store-test-results-into-db: true
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}

View File

@@ -67,7 +67,7 @@ jobs:
runs-on: ubuntu-22.04
permissions:
id-token: write # for `azure/login` and aws auth
id-token: write # for `azure/login`
steps:
- uses: docker/login-action@v3
@@ -75,15 +75,11 @@ jobs:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
- uses: docker/login-action@v3
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 3600
- name: Login to Amazon Dev ECR
uses: aws-actions/amazon-ecr-login@v2
registry: 369495373322.dkr.ecr.eu-central-1.amazonaws.com
username: ${{ secrets.AWS_ACCESS_KEY_DEV }}
password: ${{ secrets.AWS_SECRET_KEY_DEV }}
- name: Azure login
uses: azure/login@6c251865b4e6290e7b78be643ea2d005bc51f69a # @v2.1.1
@@ -98,7 +94,7 @@ jobs:
- name: Tag build-tools with `${{ env.TO_TAG }}` in Docker Hub, ECR, and ACR
env:
DEFAULT_DEBIAN_VERSION: bookworm
DEFAULT_DEBIAN_VERSION: bullseye
run: |
for debian_version in bullseye bookworm; do
tags=()

View File

@@ -1,12 +1,6 @@
name: Pre-merge checks
on:
pull_request:
paths:
- .github/workflows/_check-codestyle-python.yml
- .github/workflows/_check-codestyle-rust.yml
- .github/workflows/build-build-tools-image.yml
- .github/workflows/pre-merge-checks.yml
merge_group:
branches:
- main
@@ -23,52 +17,33 @@ jobs:
runs-on: ubuntu-22.04
outputs:
python-changed: ${{ steps.python-src.outputs.any_changed }}
rust-changed: ${{ steps.rust-src.outputs.any_changed }}
steps:
- uses: actions/checkout@v4
- uses: tj-actions/changed-files@4edd678ac3f81e2dc578756871e4d00c19191daf # v45.0.4
id: python-src
with:
files: |
.github/workflows/_check-codestyle-python.yml
.github/workflows/build-build-tools-image.yml
.github/workflows/pre-merge-checks.yml
**/**.py
poetry.lock
pyproject.toml
- uses: tj-actions/changed-files@4edd678ac3f81e2dc578756871e4d00c19191daf # v45.0.4
id: rust-src
with:
files: |
.github/workflows/_check-codestyle-rust.yml
.github/workflows/build-build-tools-image.yml
.github/workflows/pre-merge-checks.yml
**/**.rs
**/Cargo.toml
Cargo.toml
Cargo.lock
- name: PRINT ALL CHANGED FILES FOR DEBUG PURPOSES
env:
PYTHON_CHANGED_FILES: ${{ steps.python-src.outputs.all_changed_files }}
RUST_CHANGED_FILES: ${{ steps.rust-src.outputs.all_changed_files }}
run: |
echo "${PYTHON_CHANGED_FILES}"
echo "${RUST_CHANGED_FILES}"
check-build-tools-image:
if: needs.get-changed-files.outputs.python-changed == 'true'
needs: [ get-changed-files ]
uses: ./.github/workflows/check-build-tools-image.yml
build-build-tools-image:
if: |
false
|| needs.get-changed-files.outputs.python-changed == 'true'
|| needs.get-changed-files.outputs.rust-changed == 'true'
needs: [ get-changed-files ]
needs: [ check-build-tools-image ]
uses: ./.github/workflows/build-build-tools-image.yml
with:
# Build only one combination to save time
archs: '["x64"]'
debians: '["bookworm"]'
image-tag: ${{ needs.check-build-tools-image.outputs.image-tag }}
secrets: inherit
check-codestyle-python:
@@ -76,18 +51,7 @@ jobs:
needs: [ get-changed-files, build-build-tools-image ]
uses: ./.github/workflows/_check-codestyle-python.yml
with:
# `-bookworm-x64` suffix should match the combination in `build-build-tools-image`
build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm-x64
secrets: inherit
check-codestyle-rust:
if: needs.get-changed-files.outputs.rust-changed == 'true'
needs: [ get-changed-files, build-build-tools-image ]
uses: ./.github/workflows/_check-codestyle-rust.yml
with:
# `-bookworm-x64` suffix should match the combination in `build-build-tools-image`
build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm-x64
archs: '["x64"]'
build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
secrets: inherit
# To get items from the merge queue merged into main we need to satisfy "Status checks that are required".
@@ -95,15 +59,12 @@ jobs:
# - conclusion
# - neon-cloud-e2e
conclusion:
# Do not run job on Pull Requests as it interferes with the `conclusion` job from the `build_and_test` workflow
if: always() && github.event_name == 'merge_group'
if: always()
permissions:
statuses: write # for `github.repos.createCommitStatus(...)`
contents: write
needs:
- get-changed-files
- check-codestyle-python
- check-codestyle-rust
runs-on: ubuntu-22.04
steps:
- name: Create fake `neon-cloud-e2e` check
@@ -128,8 +89,6 @@ jobs:
- name: Fail the job if any of the dependencies do not succeed or skipped
run: exit 1
if: |
false
|| (needs.check-codestyle-python.result == 'skipped' && needs.get-changed-files.outputs.python-changed == 'true')
|| (needs.check-codestyle-rust.result == 'skipped' && needs.get-changed-files.outputs.rust-changed == 'true')
(contains(needs.check-codestyle-python.result, 'skipped') && needs.get-changed-files.outputs.python-changed == 'true')
|| contains(needs.*.result, 'failure')
|| contains(needs.*.result, 'cancelled')

View File

@@ -3,9 +3,8 @@ name: Create Release Branch
on:
schedule:
# It should be kept in sync with if-condition in jobs
- cron: '0 6 * * MON' # Storage release
- cron: '0 6 * * THU' # Proxy release
- cron: '0 6 * * FRI' # Storage release
- cron: '0 7 * * FRI' # Compute release
workflow_dispatch:
inputs:
create-storage-release-branch:
@@ -16,10 +15,6 @@ on:
type: boolean
description: 'Create Proxy release PR'
required: false
create-compute-release-branch:
type: boolean
description: 'Create Compute release PR'
required: false
# No permission for GITHUB_TOKEN by default; the **minimal required** set of permissions should be granted in each job.
permissions: {}
@@ -30,40 +25,83 @@ defaults:
jobs:
create-storage-release-branch:
if: ${{ github.event.schedule == '0 6 * * FRI' || inputs.create-storage-release-branch }}
if: ${{ github.event.schedule == '0 6 * * MON' || format('{0}', inputs.create-storage-release-branch) == 'true' }}
runs-on: ubuntu-22.04
permissions:
contents: write
contents: write # for `git push`
uses: ./.github/workflows/_create-release-pr.yml
with:
component-name: 'Storage'
release-branch: 'release'
secrets:
ci-access-token: ${{ secrets.CI_ACCESS_TOKEN }}
steps:
- name: Check out code
uses: actions/checkout@v4
with:
ref: main
- name: Set environment variables
run: |
echo "RELEASE_DATE=$(date +'%Y-%m-%d')" | tee -a $GITHUB_ENV
echo "RELEASE_BRANCH=rc/$(date +'%Y-%m-%d')" | tee -a $GITHUB_ENV
- name: Create release branch
run: git checkout -b $RELEASE_BRANCH
- name: Push new branch
run: git push origin $RELEASE_BRANCH
- name: Create pull request into release
env:
GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
run: |
TITLE="Storage & Compute release ${RELEASE_DATE}"
cat << EOF > body.md
## ${TITLE}
**Please merge this Pull Request using 'Create a merge commit' button**
EOF
gh pr create --title "${TITLE}" \
--body-file "body.md" \
--head "${RELEASE_BRANCH}" \
--base "release"
create-proxy-release-branch:
if: ${{ github.event.schedule == '0 6 * * THU' || inputs.create-proxy-release-branch }}
if: ${{ github.event.schedule == '0 6 * * THU' || format('{0}', inputs.create-proxy-release-branch) == 'true' }}
runs-on: ubuntu-22.04
permissions:
contents: write
contents: write # for `git push`
uses: ./.github/workflows/_create-release-pr.yml
with:
component-name: 'Proxy'
release-branch: 'release-proxy'
secrets:
ci-access-token: ${{ secrets.CI_ACCESS_TOKEN }}
steps:
- name: Check out code
uses: actions/checkout@v4
with:
ref: main
create-compute-release-branch:
if: ${{ github.event.schedule == '0 7 * * FRI' || inputs.create-compute-release-branch }}
- name: Set environment variables
run: |
echo "RELEASE_DATE=$(date +'%Y-%m-%d')" | tee -a $GITHUB_ENV
echo "RELEASE_BRANCH=rc/proxy/$(date +'%Y-%m-%d')" | tee -a $GITHUB_ENV
permissions:
contents: write
- name: Create release branch
run: git checkout -b $RELEASE_BRANCH
uses: ./.github/workflows/_create-release-pr.yml
with:
component-name: 'Compute'
release-branch: 'release-compute'
secrets:
ci-access-token: ${{ secrets.CI_ACCESS_TOKEN }}
- name: Push new branch
run: git push origin $RELEASE_BRANCH
- name: Create pull request into release
env:
GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
run: |
TITLE="Proxy release ${RELEASE_DATE}"
cat << EOF > body.md
## ${TITLE}
**Please merge this Pull Request using 'Create a merge commit' button**
EOF
gh pr create --title "${TITLE}" \
--body-file "body.md" \
--head "${RELEASE_BRANCH}" \
--base "release-proxy"

View File

@@ -4,12 +4,10 @@ on:
schedule:
- cron: '*/15 * * * *'
- cron: '25 0 * * *'
- cron: '25 1 * * 6'
jobs:
gh-workflow-stats-batch-2h:
name: GitHub Workflow Stats Batch 2 hours
if: github.event.schedule == '*/15 * * * *'
gh-workflow-stats-batch:
name: GitHub Workflow Stats Batch
runs-on: ubuntu-22.04
permissions:
actions: read
@@ -18,36 +16,14 @@ jobs:
uses: neondatabase/gh-workflow-stats-action@v0.2.1
with:
db_uri: ${{ secrets.GH_REPORT_STATS_DB_RW_CONNSTR }}
db_table: "gh_workflow_stats_neon"
db_table: "gh_workflow_stats_batch_neon"
gh_token: ${{ secrets.GITHUB_TOKEN }}
duration: '2h'
gh-workflow-stats-batch-48h:
name: GitHub Workflow Stats Batch 48 hours
if: github.event.schedule == '25 0 * * *'
runs-on: ubuntu-22.04
permissions:
actions: read
steps:
- name: Export Workflow Run for the past 48 hours
- name: Export Workflow Run for the past 24 hours
if: github.event.schedule == '25 0 * * *'
uses: neondatabase/gh-workflow-stats-action@v0.2.1
with:
db_uri: ${{ secrets.GH_REPORT_STATS_DB_RW_CONNSTR }}
db_table: "gh_workflow_stats_neon"
db_table: "gh_workflow_stats_batch_neon"
gh_token: ${{ secrets.GITHUB_TOKEN }}
duration: '48h'
gh-workflow-stats-batch-30d:
name: GitHub Workflow Stats Batch 30 days
if: github.event.schedule == '25 1 * * 6'
runs-on: ubuntu-22.04
permissions:
actions: read
steps:
- name: Export Workflow Run for the past 30 days
uses: neondatabase/gh-workflow-stats-action@v0.2.1
with:
db_uri: ${{ secrets.GH_REPORT_STATS_DB_RW_CONNSTR }}
db_table: "gh_workflow_stats_neon"
gh_token: ${{ secrets.GITHUB_TOKEN }}
duration: '720h'
duration: '24h'

View File

@@ -0,0 +1,42 @@
name: Report Workflow Stats
on:
workflow_run:
workflows:
- Add `external` label to issues and PRs created by external users
- Benchmarking
- Build and Test
- Build and Test Locally
- Build build-tools image
- Check Permissions
- Check build-tools image
- Check neon with extra platform builds
- Cloud Regression Test
- Create Release Branch
- Handle `approved-for-ci-run` label
- Lint GitHub Workflows
- Notify Slack channel about upcoming release
- Periodic pagebench performance test on dedicated EC2 machine in eu-central-1 region
- Pin build-tools image
- Prepare benchmarking databases by restoring dumps
- Push images to ACR
- Test Postgres client libraries
- Trigger E2E Tests
- cleanup caches by a branch
- Pre-merge checks
types: [completed]
jobs:
gh-workflow-stats:
name: Github Workflow Stats
runs-on: ubuntu-22.04
permissions:
actions: read
steps:
- name: Export GH Workflow Stats
uses: neondatabase/gh-workflow-stats-action@v0.1.4
with:
DB_URI: ${{ secrets.GH_REPORT_STATS_DB_RW_CONNSTR }}
DB_TABLE: "gh_workflow_stats_neon"
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
GH_RUN_ID: ${{ github.event.workflow_run.id }}

View File

@@ -51,8 +51,6 @@ jobs:
echo "tag=release-$(git rev-list --count HEAD)" | tee -a $GITHUB_OUTPUT
elif [[ "$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'"
BUILD_AND_TEST_RUN_ID=$(gh run list -b $CURRENT_BRANCH -c $CURRENT_SHA -w 'Build and Test' -L 1 --json databaseId --jq '.[].databaseId')
@@ -68,7 +66,7 @@ jobs:
GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
TAG: ${{ needs.tag.outputs.build-tag }}
steps:
- name: Wait for `promote-images-dev` job to finish
- name: Wait for `promote-images` job to finish
# It's important to have a timeout here, the script in the step can run infinitely
timeout-minutes: 60
run: |
@@ -79,17 +77,17 @@ jobs:
# For PRs we use the run id as the tag
BUILD_AND_TEST_RUN_ID=${TAG}
while true; do
conclusion=$(gh run --repo ${GITHUB_REPOSITORY} view ${BUILD_AND_TEST_RUN_ID} --json jobs --jq '.jobs[] | select(.name == "promote-images-dev") | .conclusion')
conclusion=$(gh run --repo ${GITHUB_REPOSITORY} view ${BUILD_AND_TEST_RUN_ID} --json jobs --jq '.jobs[] | select(.name == "promote-images") | .conclusion')
case "$conclusion" in
success)
break
;;
failure | cancelled | skipped)
echo "The 'promote-images-dev' job didn't succeed: '${conclusion}'. Exiting..."
echo "The 'promote-images' job didn't succeed: '${conclusion}'. Exiting..."
exit 1
;;
*)
echo "The 'promote-images-dev' hasn't succeed yet. Waiting..."
echo "The 'promote-images' hasn't succeed yet. Waiting..."
sleep 60
;;
esac

View File

@@ -1,29 +1,14 @@
# Autoscaling
/libs/vm_monitor/ @neondatabase/autoscaling
# DevProd
/.github/ @neondatabase/developer-productivity
# Compute
/pgxn/ @neondatabase/compute
/vendor/ @neondatabase/compute
/compute/ @neondatabase/compute
/compute_tools/ @neondatabase/compute
# Proxy
/libs/proxy/ @neondatabase/proxy
/proxy/ @neondatabase/proxy
# Storage
/pageserver/ @neondatabase/storage
/safekeeper/ @neondatabase/storage
/compute_tools/ @neondatabase/control-plane @neondatabase/compute
/storage_controller @neondatabase/storage
/storage_scrubber @neondatabase/storage
/libs/pageserver_api/ @neondatabase/storage
/libs/postgres_ffi/ @neondatabase/compute @neondatabase/storage
/libs/remote_storage/ @neondatabase/storage
/libs/safekeeper_api/ @neondatabase/storage
# Shared
/libs/vm_monitor/ @neondatabase/autoscaling
/pageserver/ @neondatabase/storage
/pgxn/ @neondatabase/compute
/pgxn/neon/ @neondatabase/compute @neondatabase/storage
/libs/compute_api/ @neondatabase/compute @neondatabase/control-plane
/libs/postgres_ffi/ @neondatabase/compute @neondatabase/storage
/proxy/ @neondatabase/proxy
/safekeeper/ @neondatabase/storage
/vendor/ @neondatabase/compute

1965
Cargo.lock generated

File diff suppressed because it is too large Load Diff

View File

@@ -11,7 +11,6 @@ members = [
"pageserver/pagebench",
"proxy",
"safekeeper",
"safekeeper/client",
"storage_broker",
"storage_controller",
"storage_controller/client",
@@ -35,10 +34,6 @@ members = [
"libs/vm_monitor",
"libs/walproposer",
"libs/wal_decoder",
"libs/postgres_initdb",
"libs/proxy/postgres-protocol2",
"libs/proxy/postgres-types2",
"libs/proxy/tokio-postgres2",
]
[workspace.package]
@@ -52,37 +47,37 @@ anyhow = { version = "1.0", features = ["backtrace"] }
arc-swap = "1.6"
async-compression = { version = "0.4.0", features = ["tokio", "gzip", "zstd"] }
atomic-take = "1.1.0"
backtrace = "0.3.74"
azure_core = { version = "0.19", default-features = false, features = ["enable_reqwest_rustls", "hmac_rust"] }
azure_identity = { version = "0.19", default-features = false, features = ["enable_reqwest_rustls"] }
azure_storage = { version = "0.19", default-features = false, features = ["enable_reqwest_rustls"] }
azure_storage_blobs = { version = "0.19", default-features = false, features = ["enable_reqwest_rustls"] }
flate2 = "1.0.26"
assert-json-diff = "2"
async-stream = "0.3"
async-trait = "0.1"
aws-config = { version = "1.5", default-features = false, features=["rustls", "sso"] }
aws-sdk-s3 = "1.52"
aws-sdk-iam = "1.46.0"
aws-sdk-kms = "1.47.0"
aws-smithy-async = { version = "1.2.1", default-features = false, features=["rt-tokio"] }
aws-smithy-types = "1.2"
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 = { version = "0.7.5", features = ["ws"] }
base64 = "0.13.0"
bincode = "1.3"
bindgen = "0.70"
bit_field = "0.10.2"
bstr = "1.0"
byteorder = "1.4"
bytes = "1.9"
bytes = "1.0"
camino = "1.1.6"
cfg-if = "1.0.0"
chrono = { version = "0.4", default-features = false, features = ["clock"] }
clap = { version = "4.0", features = ["derive", "env"] }
clashmap = { version = "1.0", features = ["raw-api"] }
clap = { version = "4.0", features = ["derive"] }
comfy-table = "7.1"
const_format = "0.2"
crc32c = "0.6"
diatomic-waker = { version = "0.2.3" }
dashmap = { version = "5.5.0", features = ["raw-api"] }
either = "1.8"
enum-map = "2.4.2"
enumset = "1.0.12"
@@ -111,11 +106,9 @@ hyper-util = "0.1"
tokio-tungstenite = "0.21.0"
indexmap = "2"
indoc = "2"
inferno = "0.12.0"
ipnet = "2.10.0"
ipnet = "2.9.0"
itertools = "0.10"
itoa = "1.0.11"
jemalloc_pprof = "0.6"
jsonwebtoken = "9"
lasso = "0.7"
libc = "0.2"
@@ -124,20 +117,19 @@ measured = { version = "0.0.22", features=["lasso"] }
measured-process = { version = "0.0.22" }
memoffset = "0.9"
nix = { version = "0.27", features = ["dir", "fs", "process", "socket", "signal", "poll"] }
notify = "8.0.0"
notify = "6.0.0"
num_cpus = "1.15"
num-traits = "0.2.15"
once_cell = "1.13"
opentelemetry = "0.27"
opentelemetry_sdk = "0.27"
opentelemetry-otlp = { version = "0.27", default-features = false, features = ["http-proto", "trace", "http", "reqwest-client"] }
opentelemetry-semantic-conventions = "0.27"
opentelemetry = "0.24"
opentelemetry_sdk = "0.24"
opentelemetry-otlp = { version = "0.17", default-features=false, features = ["http-proto", "trace", "http", "reqwest-client"] }
opentelemetry-semantic-conventions = "0.16"
parking_lot = "0.12"
parquet = { version = "53", default-features = false, features = ["zstd"] }
parquet_derive = "53"
pbkdf2 = { version = "0.12.1", features = ["simple", "std"] }
pin-project-lite = "0.2"
pprof = { version = "0.14", features = ["criterion", "flamegraph", "frame-pointer", "protobuf", "protobuf-codec"] }
procfs = "0.16"
prometheus = {version = "0.13", default-features=false, features = ["process"]} # removes protobuf dependency
prost = "0.13"
@@ -145,9 +137,9 @@ rand = "0.8"
redis = { version = "0.25.2", features = ["tokio-rustls-comp", "keep-alive"] }
regex = "1.10.2"
reqwest = { version = "0.12", default-features = false, features = ["rustls-tls"] }
reqwest-tracing = { version = "0.5", features = ["opentelemetry_0_27"] }
reqwest-middleware = "0.4"
reqwest-retry = "0.7"
reqwest-tracing = { version = "0.5", features = ["opentelemetry_0_24"] }
reqwest-middleware = "0.3.0"
reqwest-retry = "0.5"
routerify = "3"
rpds = "0.13"
rustc-hash = "1.1.0"
@@ -161,7 +153,7 @@ sentry = { version = "0.32", default-features = false, features = ["backtrace",
serde = { version = "1.0", features = ["derive"] }
serde_json = "1"
serde_path_to_error = "0.1"
serde_with = { version = "2.0", features = [ "base64" ] }
serde_with = "2.0"
serde_assert = "0.5.0"
sha2 = "0.10.2"
signal-hook = "0.3"
@@ -176,9 +168,9 @@ sync_wrapper = "0.1.2"
tar = "0.4"
test-context = "0.3"
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 = "1.41", features = ["macros"] }
tikv-jemallocator = "0.5"
tikv-jemalloc-ctl = "0.5"
tokio = { version = "1.17", 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"
@@ -188,15 +180,11 @@ tokio-tar = "0.3"
tokio-util = { version = "0.7.10", features = ["io", "rt"] }
toml = "0.8"
toml_edit = "0.22"
tonic = {version = "0.12.3", default-features = false, features = ["channel", "tls", "tls-roots"]}
tower = { version = "0.5.2", default-features = false }
tower-http = { version = "0.6.2", features = ["request-id", "trace"] }
tower-service = "0.3.3"
tonic = {version = "0.12.3", features = ["tls", "tls-roots"]}
tower-service = "0.3.2"
tracing = "0.1"
tracing-error = "0.2"
tracing-log = "0.2"
tracing-opentelemetry = "0.28"
tracing-serde = "0.2.0"
tracing-opentelemetry = "0.25"
tracing-subscriber = { version = "0.3", default-features = false, features = ["smallvec", "fmt", "tracing-log", "std", "env-filter", "json"] }
try-lock = "0.2.5"
twox-hash = { version = "1.6.3", default-features = false }
@@ -215,33 +203,35 @@ env_logger = "0.10"
log = "0.4"
## Libraries from neondatabase/ git forks, ideally with changes to be upstreamed
postgres = { git = "https://github.com/neondatabase/rust-postgres.git", branch = "neon" }
postgres-protocol = { git = "https://github.com/neondatabase/rust-postgres.git", branch = "neon" }
postgres-types = { git = "https://github.com/neondatabase/rust-postgres.git", branch = "neon" }
tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", branch = "neon" }
## Azure SDK crates
azure_core = { git = "https://github.com/neondatabase/azure-sdk-for-rust.git", branch = "neon", default-features = false, features = ["enable_reqwest_rustls", "hmac_rust"] }
azure_identity = { git = "https://github.com/neondatabase/azure-sdk-for-rust.git", branch = "neon", default-features = false, features = ["enable_reqwest_rustls"] }
azure_storage = { git = "https://github.com/neondatabase/azure-sdk-for-rust.git", branch = "neon", default-features = false, features = ["enable_reqwest_rustls"] }
azure_storage_blobs = { git = "https://github.com/neondatabase/azure-sdk-for-rust.git", branch = "neon", default-features = false, features = ["enable_reqwest_rustls"] }
# We want to use the 'neon' branch for these, but there's currently one
# incompatible change on the branch. See:
#
# - PR #8076 which contained changes that depended on the new changes in
# the rust-postgres crate, and
# - PR #8654 which reverted those changes and made the code in proxy incompatible
# with the tip of the 'neon' branch again.
#
# When those proxy changes are re-applied (see PR #8747), we can switch using
# the tip of the 'neon' branch again.
postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev = "20031d7a9ee1addeae6e0968e3899ae6bf01cee2" }
postgres-protocol = { git = "https://github.com/neondatabase/rust-postgres.git", rev = "20031d7a9ee1addeae6e0968e3899ae6bf01cee2" }
postgres-types = { git = "https://github.com/neondatabase/rust-postgres.git", rev = "20031d7a9ee1addeae6e0968e3899ae6bf01cee2" }
tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev = "20031d7a9ee1addeae6e0968e3899ae6bf01cee2" }
## Local libraries
compute_api = { version = "0.1", path = "./libs/compute_api/" }
consumption_metrics = { version = "0.1", path = "./libs/consumption_metrics/" }
metrics = { version = "0.1", path = "./libs/metrics/" }
pageserver = { path = "./pageserver" }
pageserver_api = { version = "0.1", path = "./libs/pageserver_api/" }
pageserver_client = { path = "./pageserver/client" }
pageserver_compaction = { version = "0.1", path = "./pageserver/compaction/" }
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_initdb = { path = "./libs/postgres_initdb" }
pq_proto = { version = "0.1", path = "./libs/pq_proto/" }
remote_storage = { version = "0.1", path = "./libs/remote_storage/" }
safekeeper_api = { version = "0.1", path = "./libs/safekeeper_api" }
safekeeper_client = { path = "./safekeeper/client" }
desim = { version = "0.1", path = "./libs/desim" }
storage_broker = { version = "0.1", path = "./storage_broker/" } # Note: main broker code is inside the binary crate, so linking with the library shouldn't be heavy.
storage_controller_client = { path = "./storage_controller/client" }
@@ -265,15 +255,13 @@ tonic-build = "0.12"
[patch.crates-io]
# Needed to get `tokio-postgres-rustls` to depend on our fork.
tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", branch = "neon" }
tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev = "20031d7a9ee1addeae6e0968e3899ae6bf01cee2" }
################# Binary contents sections
[profile.release]
# This is useful for profiling and, to some extent, debug.
# Besides, debug info should not affect the performance.
#
# NB: we also enable frame pointers for improved profiling, see .cargo/config.toml.
debug = true
# disable debug symbols for all packages except this one to decrease binaries size

View File

@@ -7,7 +7,7 @@ ARG IMAGE=build-tools
ARG TAG=pinned
ARG DEFAULT_PG_VERSION=17
ARG STABLE_PG_VERSION=16
ARG DEBIAN_VERSION=bookworm
ARG DEBIAN_VERSION=bullseye
ARG DEBIAN_FLAVOR=${DEBIAN_VERSION}-slim
# Build Postgres
@@ -45,7 +45,7 @@ COPY --chown=nonroot . .
ARG ADDITIONAL_RUSTFLAGS
RUN set -e \
&& RUSTFLAGS="-Clinker=clang -Clink-arg=-fuse-ld=mold -Clink-arg=-Wl,--no-rosegment -Cforce-frame-pointers=yes ${ADDITIONAL_RUSTFLAGS}" cargo build \
&& PQ_LIB_DIR=$(pwd)/pg_install/v${STABLE_PG_VERSION}/lib RUSTFLAGS="-Clinker=clang -Clink-arg=-fuse-ld=mold -Clink-arg=-Wl,--no-rosegment ${ADDITIONAL_RUSTFLAGS}" cargo build \
--bin pg_sni_router \
--bin pageserver \
--bin pagectl \
@@ -55,6 +55,7 @@ RUN set -e \
--bin proxy \
--bin neon_local \
--bin storage_scrubber \
--bin stream_events \
--locked --release
# Build final image
@@ -64,16 +65,11 @@ ARG DEFAULT_PG_VERSION
WORKDIR /data
RUN set -e \
&& echo 'Acquire::Retries "5";' > /etc/apt/apt.conf.d/80-retries \
&& apt update \
&& apt install -y \
libreadline-dev \
libseccomp-dev \
ca-certificates \
# System postgres for use with client libraries (e.g. in storage controller)
postgresql-15 \
openssl \
&& rm -f /etc/apt/apt.conf.d/80-retries \
&& rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* \
&& useradd -d /data neon \
&& chown -R neon:neon /data
@@ -87,6 +83,7 @@ COPY --from=build --chown=neon:neon /home/nonroot/target/release/storage_control
COPY --from=build --chown=neon:neon /home/nonroot/target/release/proxy /usr/local/bin
COPY --from=build --chown=neon:neon /home/nonroot/target/release/neon_local /usr/local/bin
COPY --from=build --chown=neon:neon /home/nonroot/target/release/storage_scrubber /usr/local/bin
COPY --from=build --chown=neon:neon /home/nonroot/target/release/stream_events /usr/local/bin
COPY --from=pg-build /home/nonroot/pg_install/v14 /usr/local/v14/
COPY --from=pg-build /home/nonroot/pg_install/v15 /usr/local/v15/
@@ -106,6 +103,11 @@ RUN mkdir -p /data/.neon/ && \
> /data/.neon/pageserver.toml && \
chown -R neon:neon /data/.neon
# When running a binary that links with libpq, default to using our most recent postgres version. Binaries
# that want a particular postgres version will select it explicitly: this is just a default.
ENV LD_LIBRARY_PATH=/usr/local/v${DEFAULT_PG_VERSION}/lib
VOLUME ["/data"]
USER neon
EXPOSE 6400

View File

@@ -3,6 +3,7 @@ ROOT_PROJECT_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
# Where to install Postgres, default is ./pg_install, maybe useful for package managers
POSTGRES_INSTALL_DIR ?= $(ROOT_PROJECT_DIR)/pg_install/
OPENSSL_PREFIX_DIR := /usr/local/openssl
ICU_PREFIX_DIR := /usr/local/icu
#
@@ -10,45 +11,33 @@ ICU_PREFIX_DIR := /usr/local/icu
# environment variable.
#
BUILD_TYPE ?= debug
WITH_SANITIZERS ?= no
ifeq ($(BUILD_TYPE),release)
PG_CONFIGURE_OPTS = --enable-debug --with-openssl
PG_CFLAGS = -O2 -g3 $(CFLAGS)
PG_LDFLAGS = $(LDFLAGS)
# Unfortunately, `--profile=...` is a nightly feature
CARGO_BUILD_FLAGS += --release
else ifeq ($(BUILD_TYPE),debug)
PG_CONFIGURE_OPTS = --enable-debug --with-openssl --enable-cassert --enable-depend
PG_CFLAGS = -O0 -g3 $(CFLAGS)
PG_LDFLAGS = $(LDFLAGS)
else
$(error Bad build type '$(BUILD_TYPE)', see Makefile for options)
endif
ifeq ($(WITH_SANITIZERS),yes)
PG_CFLAGS += -fsanitize=address -fsanitize=undefined -fno-sanitize-recover
COPT += -Wno-error # to avoid failing on warnings induced by sanitizers
PG_LDFLAGS = -fsanitize=address -fsanitize=undefined -static-libasan -static-libubsan $(LDFLAGS)
export CC := gcc
export ASAN_OPTIONS := detect_leaks=0
endif
ifeq ($(shell test -e /home/nonroot/.docker_build && echo -n yes),yes)
# Exclude static build openssl, icu for local build (MacOS, Linux)
# Only keep for build type release and debug
PG_CFLAGS += -I$(OPENSSL_PREFIX_DIR)/include
PG_CONFIGURE_OPTS += --with-icu
PG_CONFIGURE_OPTS += ICU_CFLAGS='-I/$(ICU_PREFIX_DIR)/include -DU_STATIC_IMPLEMENTATION'
PG_CONFIGURE_OPTS += ICU_LIBS='-L$(ICU_PREFIX_DIR)/lib -L$(ICU_PREFIX_DIR)/lib64 -licui18n -licuuc -licudata -lstdc++ -Wl,-Bdynamic -lm'
PG_CONFIGURE_OPTS += LDFLAGS='-L$(OPENSSL_PREFIX_DIR)/lib -L$(OPENSSL_PREFIX_DIR)/lib64 -L$(ICU_PREFIX_DIR)/lib -L$(ICU_PREFIX_DIR)/lib64 -Wl,-Bstatic -lssl -lcrypto -Wl,-Bdynamic -lrt -lm -ldl -lpthread'
endif
UNAME_S := $(shell uname -s)
ifeq ($(UNAME_S),Linux)
# Seccomp BPF is only available for Linux
ifneq ($(WITH_SANITIZERS),yes)
PG_CONFIGURE_OPTS += --with-libseccomp
endif
PG_CONFIGURE_OPTS += --with-libseccomp
else ifeq ($(UNAME_S),Darwin)
PG_CFLAGS += -DUSE_PREFETCH
ifndef DISABLE_HOMEBREW
# macOS with brew-installed openssl requires explicit paths
# It can be configured with OPENSSL_PREFIX variable
@@ -77,6 +66,8 @@ CARGO_BUILD_FLAGS += $(filter -j1,$(MAKEFLAGS))
CARGO_CMD_PREFIX += $(if $(filter n,$(MAKEFLAGS)),,+)
# Force cargo not to print progress bar
CARGO_CMD_PREFIX += CARGO_TERM_PROGRESS_WHEN=never CI=1
# Set PQ_LIB_DIR to make sure `storage_controller` get linked with bundled libpq (through diesel)
CARGO_CMD_PREFIX += PQ_LIB_DIR=$(POSTGRES_INSTALL_DIR)/v16/lib
CACHEDIR_TAG_CONTENTS := "Signature: 8a477f597d28d172789f06886806bc55"
@@ -119,7 +110,7 @@ $(POSTGRES_INSTALL_DIR)/build/%/config.status:
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-$$VERSION/configure \
CFLAGS='$(PG_CFLAGS)' LDFLAGS='$(PG_LDFLAGS)' \
CFLAGS='$(PG_CFLAGS)' \
$(PG_CONFIGURE_OPTS) --with-extra-version=" ($$EXTRA_VERSION)" \
--prefix=$(abspath $(POSTGRES_INSTALL_DIR))/$$VERSION > configure.log)
@@ -155,8 +146,6 @@ postgres-%: postgres-configure-% \
$(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 amcheck $*"

View File

@@ -21,10 +21,8 @@ The Neon storage engine consists of two major components:
See developer documentation in [SUMMARY.md](/docs/SUMMARY.md) for more information.
## Running a local development environment
## Running local installation
Neon can be run on a workstation for small experiments and to test code changes, by
following these instructions.
#### Installing dependencies on Linux
1. Install build dependencies and other applicable packages
@@ -134,7 +132,7 @@ make -j`sysctl -n hw.logicalcpu` -s
To run the `psql` client, install the `postgresql-client` package or modify `PATH` and `LD_LIBRARY_PATH` to include `pg_install/bin` and `pg_install/lib`, respectively.
To run the integration tests or Python scripts (not required to use the code), install
Python (3.11 or higher), and install the python3 packages using `./scripts/pysync` (requires [poetry>=1.8](https://python-poetry.org/)) in the project directory.
Python (3.9 or higher), and install the python3 packages using `./scripts/pysync` (requires [poetry>=1.8](https://python-poetry.org/)) in the project directory.
#### Running neon database
@@ -240,7 +238,7 @@ postgres=# select * from t;
> cargo neon stop
```
More advanced usages can be found at [Local Development Control Plane (`neon_local`))](./control_plane/README.md).
More advanced usages can be found at [Control Plane and Neon Local](./control_plane/README.md).
#### Handling build failures

View File

@@ -1,19 +1,8 @@
ARG DEBIAN_VERSION=bookworm
ARG DEBIAN_VERSION=bullseye
FROM debian:bookworm-slim AS pgcopydb_builder
ARG DEBIAN_VERSION
# Use strict mode for bash to catch errors early
SHELL ["/bin/bash", "-euo", "pipefail", "-c"]
# By default, /bin/sh used in debian images will treat '\n' as eol,
# but as we use bash as SHELL, and built-in echo in bash requires '-e' flag for that.
RUN echo 'Acquire::Retries "5";' > /etc/apt/apt.conf.d/80-retries && \
echo -e "retry_connrefused = on\ntimeout=15\ntries=5\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
RUN if [ "${DEBIAN_VERSION}" = "bookworm" ]; then \
set -e && \
apt update && \
@@ -46,7 +35,6 @@ RUN if [ "${DEBIAN_VERSION}" = "bookworm" ]; then \
mkdir /tmp/pgcopydb && \
tar -xzf /tmp/pgcopydb.tar.gz -C /tmp/pgcopydb --strip-components=1 && \
cd /tmp/pgcopydb && \
patch -p1 < /pgcopydbv017.patch && \
make -s clean && \
make -s -j12 install && \
libpq_path=$(find /lib /usr/lib -name "libpq.so.5" | head -n 1) && \
@@ -63,20 +51,15 @@ ARG DEBIAN_VERSION
# Add nonroot user
RUN useradd -ms /bin/bash nonroot -b /home
# Use strict mode for bash to catch errors early
SHELL ["/bin/bash", "-euo", "pipefail", "-c"]
SHELL ["/bin/bash", "-c"]
RUN mkdir -p /pgcopydb/bin && \
mkdir -p /pgcopydb/lib && \
chmod -R 755 /pgcopydb && \
chown -R nonroot:nonroot /pgcopydb
COPY --from=pgcopydb_builder /usr/lib/postgresql/16/bin/pgcopydb /pgcopydb/bin/pgcopydb
COPY --from=pgcopydb_builder /pgcopydb/lib/libpq.so.5 /pgcopydb/lib/libpq.so.5
RUN echo 'Acquire::Retries "5";' > /etc/apt/apt.conf.d/80-retries && \
echo -e "retry_connrefused = on\ntimeout=15\ntries=5\n" > /root/.wgetrc && \
echo -e "--retry-connrefused\n--connect-timeout 15\n--retry 5\n--max-time 300\n" > /root/.curlrc
COPY --from=pgcopydb_builder /usr/lib/postgresql/16/bin/pgcopydb /pgcopydb/bin/pgcopydb
COPY --from=pgcopydb_builder /pgcopydb/lib/libpq.so.5 /pgcopydb/lib/libpq.so.5
# System deps
#
@@ -132,7 +115,7 @@ RUN set -e \
# Keep the version the same as in compute/compute-node.Dockerfile and
# test_runner/regress/test_compute_metrics.py.
ENV SQL_EXPORTER_VERSION=0.17.0
ENV SQL_EXPORTER_VERSION=0.13.1
RUN curl -fsSL \
"https://github.com/burningalchemist/sql_exporter/releases/download/${SQL_EXPORTER_VERSION}/sql_exporter-${SQL_EXPORTER_VERSION}.linux-$(case "$(uname -m)" in x86_64) echo amd64;; aarch64) echo arm64;; esac).tar.gz" \
--output sql_exporter.tar.gz \
@@ -199,20 +182,29 @@ RUN set -e \
# It includes several bug fixes on top on v2.0 release (https://github.com/linux-test-project/lcov/compare/v2.0...master)
# And patches from us:
# - Generates json file with code coverage summary (https://github.com/neondatabase/lcov/commit/426e7e7a22f669da54278e9b55e6d8caabd00af0.tar.gz)
RUN set +o pipefail && \
for package in Capture::Tiny DateTime Devel::Cover Digest::MD5 File::Spec JSON::XS Memory::Process Time::HiRes JSON; do \
yes | perl -MCPAN -e "CPAN::Shell->notest('install', '$package')";\
done && \
set -o pipefail
# Split into separate step to debug flaky failures here
RUN wget https://github.com/neondatabase/lcov/archive/426e7e7a22f669da54278e9b55e6d8caabd00af0.tar.gz -O lcov.tar.gz \
&& ls -laht lcov.tar.gz && sha256sum lcov.tar.gz \
RUN for package in Capture::Tiny DateTime Devel::Cover Digest::MD5 File::Spec JSON::XS Memory::Process Time::HiRes JSON; do yes | perl -MCPAN -e "CPAN::Shell->notest('install', '$package')"; done \
&& wget https://github.com/neondatabase/lcov/archive/426e7e7a22f669da54278e9b55e6d8caabd00af0.tar.gz -O lcov.tar.gz \
&& echo "61a22a62e20908b8b9e27d890bd0ea31f567a7b9668065589266371dcbca0992 lcov.tar.gz" | sha256sum --check \
&& mkdir -p lcov && tar -xzf lcov.tar.gz -C lcov --strip-components=1 \
&& cd lcov \
&& make install \
&& rm -rf ../lcov.tar.gz
# Compile and install the static OpenSSL library
ENV OPENSSL_VERSION=1.1.1w
ENV OPENSSL_PREFIX=/usr/local/openssl
RUN wget -O /tmp/openssl-${OPENSSL_VERSION}.tar.gz https://www.openssl.org/source/openssl-${OPENSSL_VERSION}.tar.gz && \
echo "cf3098950cb4d853ad95c0841f1f9c6d3dc102dccfcacd521d93925208b76ac8 /tmp/openssl-${OPENSSL_VERSION}.tar.gz" | sha256sum --check && \
cd /tmp && \
tar xzvf /tmp/openssl-${OPENSSL_VERSION}.tar.gz && \
rm /tmp/openssl-${OPENSSL_VERSION}.tar.gz && \
cd /tmp/openssl-${OPENSSL_VERSION} && \
./config --prefix=${OPENSSL_PREFIX} -static --static no-shared -fPIC && \
make -j "$(nproc)" && \
make install && \
cd /tmp && \
rm -rf /tmp/openssl-${OPENSSL_VERSION}
# Use the same version of libicu as the compute nodes so that
# clusters created using inidb on pageserver can be used by computes.
#
@@ -241,10 +233,8 @@ RUN wget -O /tmp/libicu-${ICU_VERSION}.tgz https://github.com/unicode-org/icu/re
USER nonroot:nonroot
WORKDIR /home/nonroot
RUN echo -e "--retry-connrefused\n--connect-timeout 15\n--retry 5\n--max-time 300\n" > /home/nonroot/.curlrc
# Python
ENV PYTHON_VERSION=3.11.10 \
ENV PYTHON_VERSION=3.9.19 \
PYENV_ROOT=/home/nonroot/.pyenv \
PATH=/home/nonroot/.pyenv/shims:/home/nonroot/.pyenv/bin:/home/nonroot/.poetry/bin:$PATH
RUN set -e \
@@ -268,15 +258,14 @@ 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=1.84.1
ENV RUSTC_VERSION=1.82.0
ENV RUSTUP_HOME="/home/nonroot/.rustup"
ENV PATH="/home/nonroot/.cargo/bin:${PATH}"
ARG RUSTFILT_VERSION=0.2.1
ARG CARGO_HAKARI_VERSION=0.9.33
ARG CARGO_DENY_VERSION=0.16.2
ARG CARGO_HACK_VERSION=0.6.33
ARG CARGO_NEXTEST_VERSION=0.9.85
ARG CARGO_DIESEL_CLI_VERSION=2.2.6
ARG CARGO_HAKARI_VERSION=0.9.30
ARG CARGO_DENY_VERSION=0.16.1
ARG CARGO_HACK_VERSION=0.6.31
ARG CARGO_NEXTEST_VERSION=0.9.72
RUN curl -sSO https://static.rust-lang.org/rustup/dist/$(uname -m)-unknown-linux-gnu/rustup-init && whoami && \
chmod +x rustup-init && \
./rustup-init -y --default-toolchain ${RUSTC_VERSION} && \
@@ -290,8 +279,6 @@ RUN curl -sSO https://static.rust-lang.org/rustup/dist/$(uname -m)-unknown-linux
cargo install cargo-deny --locked --version ${CARGO_DENY_VERSION} && \
cargo install cargo-hack --version ${CARGO_HACK_VERSION} && \
cargo install cargo-nextest --version ${CARGO_NEXTEST_VERSION} && \
cargo install diesel_cli --version ${CARGO_DIESEL_CLI_VERSION} \
--features postgres-bundled --no-default-features && \
rm -rf /home/nonroot/.cargo/registry && \
rm -rf /home/nonroot/.cargo/git
@@ -302,7 +289,7 @@ RUN whoami \
&& cargo --version --verbose \
&& rustup --version --verbose \
&& rustc --version --verbose \
&& clang --version
&& clang --version
RUN if [ "${DEBIAN_VERSION}" = "bookworm" ]; then \
LD_LIBRARY_PATH=/pgcopydb/lib /pgcopydb/bin/pgcopydb --version; \

View File

@@ -1,57 +0,0 @@
diff --git a/src/bin/pgcopydb/copydb.c b/src/bin/pgcopydb/copydb.c
index d730b03..69a9be9 100644
--- a/src/bin/pgcopydb/copydb.c
+++ b/src/bin/pgcopydb/copydb.c
@@ -44,6 +44,7 @@ GUC dstSettings[] = {
{ "synchronous_commit", "'off'" },
{ "statement_timeout", "0" },
{ "lock_timeout", "0" },
+ { "idle_in_transaction_session_timeout", "0" },
{ NULL, NULL },
};
diff --git a/src/bin/pgcopydb/pgsql.c b/src/bin/pgcopydb/pgsql.c
index 94f2f46..e051ba8 100644
--- a/src/bin/pgcopydb/pgsql.c
+++ b/src/bin/pgcopydb/pgsql.c
@@ -2319,6 +2319,11 @@ pgsql_execute_log_error(PGSQL *pgsql,
LinesBuffer lbuf = { 0 };
+ if (message != NULL){
+ // make sure message is writable by splitLines
+ message = strdup(message);
+ }
+
if (!splitLines(&lbuf, message))
{
/* errors have already been logged */
@@ -2332,6 +2337,7 @@ pgsql_execute_log_error(PGSQL *pgsql,
PQbackendPID(pgsql->connection),
lbuf.lines[lineNumber]);
}
+ free(message); // free copy of message we created above
if (pgsql->logSQL)
{
@@ -3174,11 +3180,18 @@ pgcopy_log_error(PGSQL *pgsql, PGresult *res, const char *context)
/* errors have already been logged */
return;
}
-
if (res != NULL)
{
char *sqlstate = PQresultErrorField(res, PG_DIAG_SQLSTATE);
- strlcpy(pgsql->sqlstate, sqlstate, sizeof(pgsql->sqlstate));
+ if (sqlstate == NULL)
+ {
+ // PQresultErrorField returned NULL!
+ pgsql->sqlstate[0] = '\0'; // Set to an empty string to avoid segfault
+ }
+ else
+ {
+ strlcpy(pgsql->sqlstate, sqlstate, sizeof(pgsql->sqlstate));
+ }
}
char *endpoint =

File diff suppressed because it is too large Load Diff

View File

@@ -3,11 +3,9 @@
metrics: [
import 'sql_exporter/checkpoints_req.libsonnet',
import 'sql_exporter/checkpoints_timed.libsonnet',
import 'sql_exporter/compute_backpressure_throttling_seconds_total.libsonnet',
import 'sql_exporter/compute_backpressure_throttling_seconds.libsonnet',
import 'sql_exporter/compute_current_lsn.libsonnet',
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_receive_lsn.libsonnet',
import 'sql_exporter/compute_subscriptions_count.libsonnet',
import 'sql_exporter/connection_counts.libsonnet',

View File

@@ -1,9 +1,5 @@
[databases]
;; pgbouncer propagates application_name (if it's specified) to the server, but some
;; clients don't set it. We set default application_name=pgbouncer to make it
;; easier to identify pgbouncer connections in Postgres. If client sets
;; application_name, it will be used instead.
*=host=localhost port=5432 auth_user=cloud_admin application_name=pgbouncer
*=host=localhost port=5432 auth_user=cloud_admin
[pgbouncer]
listen_port=6432
listen_addr=0.0.0.0
@@ -19,12 +15,3 @@ max_prepared_statements=0
admin_users=postgres
unix_socket_dir=/tmp/
unix_socket_mode=0777
; required for pgbouncer_exporter
ignore_startup_parameters=extra_float_digits
;; 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
;; the past where the logging significantly stressed the log device or pgbouncer
;; itself.
log_connections=0
log_disconnections=0

View File

@@ -1,10 +1,10 @@
{
metric_name: 'compute_backpressure_throttling_seconds_total',
type: 'counter',
metric_name: 'compute_backpressure_throttling_seconds',
type: 'gauge',
help: 'Time compute has spent throttled',
key_labels: null,
values: [
'throttled',
],
query: importstr 'sql_exporter/compute_backpressure_throttling_seconds_total.sql',
query: importstr 'sql_exporter/compute_backpressure_throttling_seconds.sql',
}

View File

@@ -1,7 +0,0 @@
SELECT
(SELECT current_setting('neon.timeline_id')) AS timeline_id,
-- Postgres creates temporary snapshot files of the form %X-%X.snap.%d.tmp.
-- These temporary snapshot files are renamed to the actual snapshot files
-- after they are completely built. We only WAL-log the completely built
-- snapshot files
(SELECT COALESCE(sum(size), 0) FROM pg_ls_logicalsnapdir() WHERE name LIKE '%.snap') AS logical_snapshots_bytes;

View File

@@ -1,17 +0,0 @@
local neon = import 'neon.libsonnet';
local pg_ls_logicalsnapdir = importstr 'sql_exporter/compute_logical_snapshots_bytes.15.sql';
local pg_ls_dir = importstr 'sql_exporter/compute_logical_snapshots_bytes.sql';
{
metric_name: 'compute_logical_snapshots_bytes',
type: 'gauge',
help: 'Size of the pg_logical/snapshots directory, not including temporary files',
key_labels: [
'timeline_id',
],
values: [
'logical_snapshots_bytes',
],
query: if neon.PG_MAJORVERSION_NUM < 15 then pg_ls_dir else pg_ls_logicalsnapdir,
}

View File

@@ -1,9 +0,0 @@
SELECT
(SELECT setting FROM pg_settings WHERE name = 'neon.timeline_id') AS timeline_id,
-- Postgres creates temporary snapshot files of the form %X-%X.snap.%d.tmp.
-- These temporary snapshot files are renamed to the actual snapshot files
-- after they are completely built. We only WAL-log the completely built
-- snapshot files
(SELECT COALESCE(sum((pg_stat_file('pg_logical/snapshots/' || name, missing_ok => true)).size), 0)
FROM (SELECT * FROM pg_ls_dir('pg_logical/snapshots') WHERE pg_ls_dir LIKE '%.snap') AS name
) AS logical_snapshots_bytes;

View File

@@ -1,10 +0,0 @@
{
metric_name: 'compute_max_connections',
type: 'gauge',
help: 'Max connections allowed for Postgres',
key_labels: null,
values: [
'max_connections',
],
query: importstr 'sql_exporter/compute_max_connections.sql',
}

View File

@@ -1 +0,0 @@
SELECT current_setting('max_connections') as max_connections;

View File

@@ -147,7 +147,7 @@ index 542c2e098c..0062d3024f 100644
ALTER TABLE ptnowner1 OWNER TO regress_ptnowner;
ALTER TABLE ptnowner OWNER TO regress_ptnowner;
diff --git a/src/test/regress/expected/collate.icu.utf8.out b/src/test/regress/expected/collate.icu.utf8.out
index 3f9a8f539c..0a51b52940 100644
index 97bbe53b64..eac3d42a79 100644
--- a/src/test/regress/expected/collate.icu.utf8.out
+++ b/src/test/regress/expected/collate.icu.utf8.out
@@ -1016,7 +1016,7 @@ select * from collate_test1 where b ilike 'ABC';
@@ -309,7 +309,7 @@ index b48365ec98..a6ef910055 100644
-- the wrong partition. This test is *not* guaranteed to trigger that bug, but
-- does so when shared_buffers is small enough. To test if we encountered the
diff --git a/src/test/regress/expected/copy2.out b/src/test/regress/expected/copy2.out
index 9a74820ee8..22400a5551 100644
index faf1a4d1b0..a44c97db52 100644
--- a/src/test/regress/expected/copy2.out
+++ b/src/test/regress/expected/copy2.out
@@ -553,8 +553,8 @@ select * from check_con_tbl;
@@ -573,7 +573,7 @@ index 93302a07ef..1a73f083ac 100644
-- that does not match with what's expected.
-- This checks all the object types that include schema qualifications.
diff --git a/src/test/regress/expected/create_view.out b/src/test/regress/expected/create_view.out
index f551624afb..57f1e432d4 100644
index f3f8c7b5a2..3e3e54ff4c 100644
--- a/src/test/regress/expected/create_view.out
+++ b/src/test/regress/expected/create_view.out
@@ -18,7 +18,8 @@ CREATE TABLE real_city (
@@ -700,12 +700,12 @@ index 6ed50fdcfa..caa00a345d 100644
COMMENT ON FOREIGN DATA WRAPPER dummy IS 'useless';
CREATE FOREIGN DATA WRAPPER postgresql VALIDATOR postgresql_fdw_validator;
diff --git a/src/test/regress/expected/foreign_key.out b/src/test/regress/expected/foreign_key.out
index 6b8c2f2414..8e13b7fa46 100644
index 12e523c737..8872e23935 100644
--- a/src/test/regress/expected/foreign_key.out
+++ b/src/test/regress/expected/foreign_key.out
@@ -1985,7 +1985,7 @@ ALTER TABLE fk_partitioned_fk_6 ATTACH PARTITION fk_partitioned_pk_6 FOR VALUES
ERROR: cannot ALTER TABLE "fk_partitioned_pk_61" because it is being used by active queries in this session
DROP TABLE fk_partitioned_pk_6, fk_partitioned_fk_6;
@@ -1968,7 +1968,7 @@ ALTER TABLE fk_partitioned_fk ATTACH PARTITION fk_partitioned_fk_2
FOR VALUES IN (1600);
-- leave these tables around intentionally
-- test the case when the referenced table is owned by a different user
-create role regress_other_partitioned_fk_owner;
+create role regress_other_partitioned_fk_owner PASSWORD NEON_PASSWORD_PLACEHOLDER;
@@ -713,7 +713,7 @@ index 6b8c2f2414..8e13b7fa46 100644
set role regress_other_partitioned_fk_owner;
create table other_partitioned_fk(a int, b int) partition by list (a);
diff --git a/src/test/regress/expected/generated.out b/src/test/regress/expected/generated.out
index 5881420388..4ae21aa43c 100644
index 0f623f7119..b48588a54e 100644
--- a/src/test/regress/expected/generated.out
+++ b/src/test/regress/expected/generated.out
@@ -534,7 +534,7 @@ CREATE TABLE gtest10a (a int PRIMARY KEY, b int GENERATED ALWAYS AS (a * 2) STOR
@@ -762,7 +762,7 @@ index a2036a1597..805d73b9d2 100644
-- fields, leading to long bucket chains and lots of table expansion.
-- this is therefore a stress test of the bucket overflow code (unlike
diff --git a/src/test/regress/expected/identity.out b/src/test/regress/expected/identity.out
index 1b74958de9..078187b542 100644
index cc7772349f..98a08eb48d 100644
--- a/src/test/regress/expected/identity.out
+++ b/src/test/regress/expected/identity.out
@@ -520,7 +520,7 @@ ALTER TABLE itest7 ALTER COLUMN a SET GENERATED BY DEFAULT;
@@ -775,10 +775,10 @@ index 1b74958de9..078187b542 100644
GRANT SELECT, INSERT ON itest8 TO regress_identity_user1;
SET ROLE regress_identity_user1;
diff --git a/src/test/regress/expected/inherit.out b/src/test/regress/expected/inherit.out
index 8f831c95c3..ec681b52af 100644
index 4943429e9b..0257f22b15 100644
--- a/src/test/regress/expected/inherit.out
+++ b/src/test/regress/expected/inherit.out
@@ -2636,7 +2636,7 @@ create index on permtest_parent (left(c, 3));
@@ -2606,7 +2606,7 @@ create index on permtest_parent (left(c, 3));
insert into permtest_parent
select 1, 'a', left(fipshash(i::text), 5) from generate_series(0, 100) i;
analyze permtest_parent;
@@ -981,7 +981,7 @@ index fc42d418bf..e38f517574 100644
CREATE SCHEMA addr_nsp;
SET search_path TO 'addr_nsp';
diff --git a/src/test/regress/expected/password.out b/src/test/regress/expected/password.out
index 8475231735..0653946337 100644
index 8475231735..1afae5395f 100644
--- a/src/test/regress/expected/password.out
+++ b/src/test/regress/expected/password.out
@@ -12,11 +12,11 @@ SET password_encryption = 'md5'; -- ok
@@ -1006,63 +1006,65 @@ index 8475231735..0653946337 100644
-----------------+---------------------------------------------------
- regress_passwd1 | md5783277baca28003b33453252be4dbb34
- regress_passwd2 | md54044304ba511dd062133eb5b4b84a2a3
+ regress_passwd1 | NEON_MD5_PLACEHOLDER:regress_passwd1
+ regress_passwd2 | NEON_MD5_PLACEHOLDER:regress_passwd2
+ regress_passwd1 | NEON_MD5_PLACEHOLDER_regress_passwd1
+ regress_passwd2 | NEON_MD5_PLACEHOLDER_regress_passwd2
regress_passwd3 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
- regress_passwd4 |
+ regress_passwd4 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
(4 rows)
-- Rename a role
@@ -54,24 +54,16 @@ ALTER ROLE regress_passwd2_new RENAME TO regress_passwd2;
@@ -54,24 +54,30 @@ ALTER ROLE regress_passwd2_new RENAME TO regress_passwd2;
-- passwords.
SET password_encryption = 'md5';
-- encrypt with MD5
-ALTER ROLE regress_passwd2 PASSWORD 'foo';
--- already encrypted, use as they are
-ALTER ROLE regress_passwd1 PASSWORD 'md5cd3578025fe2c3d7ed1b9a9b26238b70';
-ALTER ROLE regress_passwd3 PASSWORD 'SCRAM-SHA-256$4096:VLK4RMaQLCvNtQ==$6YtlR4t69SguDiwFvbVgVZtuz6gpJQQqUMZ7IQJK5yI=:ps75jrHeYU4lXCcXI4O8oIdJ3eO8o2jirjruw9phBTo=';
+ALTER ROLE regress_passwd2 PASSWORD NEON_PASSWORD_PLACEHOLDER;
-- already encrypted, use as they are
ALTER ROLE regress_passwd1 PASSWORD 'md5cd3578025fe2c3d7ed1b9a9b26238b70';
+ERROR: Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
ALTER ROLE regress_passwd3 PASSWORD 'SCRAM-SHA-256$4096:VLK4RMaQLCvNtQ==$6YtlR4t69SguDiwFvbVgVZtuz6gpJQQqUMZ7IQJK5yI=:ps75jrHeYU4lXCcXI4O8oIdJ3eO8o2jirjruw9phBTo=';
+ERROR: Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
SET password_encryption = 'scram-sha-256';
-- create SCRAM secret
-ALTER ROLE regress_passwd4 PASSWORD 'foo';
--- already encrypted with MD5, use as it is
-CREATE ROLE regress_passwd5 PASSWORD 'md5e73a4b11df52a6068f8b39f90be36023';
--- This looks like a valid SCRAM-SHA-256 secret, but it is not
--- so it should be hashed with SCRAM-SHA-256.
-CREATE ROLE regress_passwd6 PASSWORD 'SCRAM-SHA-256$1234';
--- These may look like valid MD5 secrets, but they are not, so they
--- should be hashed with SCRAM-SHA-256.
--- trailing garbage at the end
-CREATE ROLE regress_passwd7 PASSWORD 'md5012345678901234567890123456789zz';
--- invalid length
-CREATE ROLE regress_passwd8 PASSWORD 'md501234567890123456789012345678901zz';
+ALTER ROLE regress_passwd4 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+-- Neon does not support encrypted passwords, use unencrypted instead
+CREATE ROLE regress_passwd5 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+-- Neon does not support encrypted passwords, use unencrypted instead
+CREATE ROLE regress_passwd6 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+CREATE ROLE regress_passwd7 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+CREATE ROLE regress_passwd8 PASSWORD NEON_PASSWORD_PLACEHOLDER;
-- already encrypted with MD5, use as it is
CREATE ROLE regress_passwd5 PASSWORD 'md5e73a4b11df52a6068f8b39f90be36023';
+ERROR: Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
-- This looks like a valid SCRAM-SHA-256 secret, but it is not
-- so it should be hashed with SCRAM-SHA-256.
CREATE ROLE regress_passwd6 PASSWORD 'SCRAM-SHA-256$1234';
+ERROR: Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
-- These may look like valid MD5 secrets, but they are not, so they
-- should be hashed with SCRAM-SHA-256.
-- trailing garbage at the end
CREATE ROLE regress_passwd7 PASSWORD 'md5012345678901234567890123456789zz';
+ERROR: Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
-- invalid length
CREATE ROLE regress_passwd8 PASSWORD 'md501234567890123456789012345678901zz';
+ERROR: Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
-- Changing the SCRAM iteration count
SET scram_iterations = 1024;
CREATE ROLE regress_passwd9 PASSWORD 'alterediterationcount';
@@ -81,11 +73,11 @@ SELECT rolname, regexp_replace(rolpassword, '(SCRAM-SHA-256)\$(\d+):([a-zA-Z0-9+
@@ -81,63 +87,67 @@ SELECT rolname, regexp_replace(rolpassword, '(SCRAM-SHA-256)\$(\d+):([a-zA-Z0-9+
ORDER BY rolname, rolpassword;
rolname | rolpassword_masked
-----------------+---------------------------------------------------
- regress_passwd1 | md5cd3578025fe2c3d7ed1b9a9b26238b70
- regress_passwd2 | md5dfa155cadd5f4ad57860162f3fab9cdb
+ regress_passwd1 | NEON_MD5_PLACEHOLDER:regress_passwd1
+ regress_passwd2 | NEON_MD5_PLACEHOLDER:regress_passwd2
+ regress_passwd1 | NEON_MD5_PLACEHOLDER_regress_passwd1
+ regress_passwd2 | NEON_MD5_PLACEHOLDER_regress_passwd2
regress_passwd3 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
regress_passwd4 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
- regress_passwd5 | md5e73a4b11df52a6068f8b39f90be36023
+ regress_passwd5 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
regress_passwd6 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
regress_passwd7 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
regress_passwd8 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
@@ -95,23 +87,20 @@ SELECT rolname, regexp_replace(rolpassword, '(SCRAM-SHA-256)\$(\d+):([a-zA-Z0-9+
- regress_passwd6 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
- regress_passwd7 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
- regress_passwd8 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
regress_passwd9 | SCRAM-SHA-256$1024:<salt>$<storedkey>:<serverkey>
-(9 rows)
+(5 rows)
-- An empty password is not allowed, in any form
CREATE ROLE regress_passwd_empty PASSWORD '';
NOTICE: empty string is not a valid password, clearing password
@@ -1080,39 +1082,58 @@ index 8475231735..0653946337 100644
-(1 row)
+(0 rows)
--- Test with invalid stored and server keys.
---
--- The first is valid, to act as a control. The others have too long
--- stored/server keys. They will be re-hashed.
-CREATE ROLE regress_passwd_sha_len0 PASSWORD 'SCRAM-SHA-256$4096:A6xHKoH/494E941doaPOYg==$Ky+A30sewHIH3VHQLRN9vYsuzlgNyGNKCh37dy96Rqw=:COPdlNiIkrsacU5QoxydEuOH6e/KfiipeETb/bPw8ZI=';
-CREATE ROLE regress_passwd_sha_len1 PASSWORD 'SCRAM-SHA-256$4096:A6xHKoH/494E941doaPOYg==$Ky+A30sewHIH3VHQLRN9vYsuzlgNyGNKCh37dy96RqwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=:COPdlNiIkrsacU5QoxydEuOH6e/KfiipeETb/bPw8ZI=';
-CREATE ROLE regress_passwd_sha_len2 PASSWORD 'SCRAM-SHA-256$4096:A6xHKoH/494E941doaPOYg==$Ky+A30sewHIH3VHQLRN9vYsuzlgNyGNKCh37dy96Rqw=:COPdlNiIkrsacU5QoxydEuOH6e/KfiipeETb/bPw8ZIAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=';
+-- Neon does not support encrypted passwords, use unencrypted instead
+CREATE ROLE regress_passwd_sha_len0 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+CREATE ROLE regress_passwd_sha_len1 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+CREATE ROLE regress_passwd_sha_len2 PASSWORD NEON_PASSWORD_PLACEHOLDER;
-- Test with invalid stored and server keys.
--
-- The first is valid, to act as a control. The others have too long
-- stored/server keys. They will be re-hashed.
CREATE ROLE regress_passwd_sha_len0 PASSWORD 'SCRAM-SHA-256$4096:A6xHKoH/494E941doaPOYg==$Ky+A30sewHIH3VHQLRN9vYsuzlgNyGNKCh37dy96Rqw=:COPdlNiIkrsacU5QoxydEuOH6e/KfiipeETb/bPw8ZI=';
+ERROR: Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
CREATE ROLE regress_passwd_sha_len1 PASSWORD 'SCRAM-SHA-256$4096:A6xHKoH/494E941doaPOYg==$Ky+A30sewHIH3VHQLRN9vYsuzlgNyGNKCh37dy96RqwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=:COPdlNiIkrsacU5QoxydEuOH6e/KfiipeETb/bPw8ZI=';
+ERROR: Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
CREATE ROLE regress_passwd_sha_len2 PASSWORD 'SCRAM-SHA-256$4096:A6xHKoH/494E941doaPOYg==$Ky+A30sewHIH3VHQLRN9vYsuzlgNyGNKCh37dy96Rqw=:COPdlNiIkrsacU5QoxydEuOH6e/KfiipeETb/bPw8ZIAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=';
+ERROR: Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
-- Check that the invalid secrets were re-hashed. A re-hashed secret
-- should not contain the original salt.
SELECT rolname, rolpassword not like '%A6xHKoH/494E941doaPOYg==%' as is_rolpassword_rehashed
@@ -120,7 +109,7 @@ SELECT rolname, rolpassword not like '%A6xHKoH/494E941doaPOYg==%' as is_rolpassw
FROM pg_authid
WHERE rolname LIKE 'regress_passwd_sha_len%'
ORDER BY rolname;
rolname | is_rolpassword_rehashed
-------------------------+-------------------------
- rolname | is_rolpassword_rehashed
--------------------------+-------------------------
- regress_passwd_sha_len0 | f
+ regress_passwd_sha_len0 | t
regress_passwd_sha_len1 | t
regress_passwd_sha_len2 | t
(3 rows)
@@ -135,6 +124,7 @@ DROP ROLE regress_passwd7;
- regress_passwd_sha_len1 | t
- regress_passwd_sha_len2 | t
-(3 rows)
+ rolname | is_rolpassword_rehashed
+---------+-------------------------
+(0 rows)
DROP ROLE regress_passwd1;
DROP ROLE regress_passwd2;
DROP ROLE regress_passwd3;
DROP ROLE regress_passwd4;
DROP ROLE regress_passwd5;
+ERROR: role "regress_passwd5" does not exist
DROP ROLE regress_passwd6;
+ERROR: role "regress_passwd6" does not exist
DROP ROLE regress_passwd7;
+ERROR: role "regress_passwd7" does not exist
DROP ROLE regress_passwd8;
+ERROR: role "regress_passwd8" does not exist
DROP ROLE regress_passwd9;
DROP ROLE regress_passwd_empty;
+ERROR: role "regress_passwd_empty" does not exist
DROP ROLE regress_passwd_sha_len0;
+ERROR: role "regress_passwd_sha_len0" does not exist
DROP ROLE regress_passwd_sha_len1;
+ERROR: role "regress_passwd_sha_len1" does not exist
DROP ROLE regress_passwd_sha_len2;
+ERROR: role "regress_passwd_sha_len2" does not exist
-- all entries should have been removed
SELECT rolname, rolpassword
FROM pg_authid
diff --git a/src/test/regress/expected/privileges.out b/src/test/regress/expected/privileges.out
index 5b9dba7b32..cc408dad42 100644
index fbb0489a4f..2905194e2c 100644
--- a/src/test/regress/expected/privileges.out
+++ b/src/test/regress/expected/privileges.out
@@ -20,19 +20,19 @@ SELECT lo_unlink(oid) FROM pg_largeobject_metadata WHERE oid >= 1000 AND oid < 3
@@ -1164,7 +1185,7 @@ index 5b9dba7b32..cc408dad42 100644
GRANT pg_read_all_data TO regress_priv_user6;
GRANT pg_write_all_data TO regress_priv_user7;
GRANT pg_read_all_settings TO regress_priv_user8 WITH ADMIN OPTION;
@@ -212,8 +212,8 @@ REVOKE pg_read_all_settings FROM regress_priv_user8;
@@ -145,8 +145,8 @@ REVOKE pg_read_all_settings FROM regress_priv_user8;
DROP USER regress_priv_user10;
DROP USER regress_priv_user9;
DROP USER regress_priv_user8;
@@ -1175,7 +1196,7 @@ index 5b9dba7b32..cc408dad42 100644
ALTER GROUP regress_priv_group1 ADD USER regress_priv_user4;
GRANT regress_priv_group2 TO regress_priv_user2 GRANTED BY regress_priv_user1;
SET SESSION AUTHORIZATION regress_priv_user1;
@@ -239,12 +239,16 @@ GRANT regress_priv_role TO regress_priv_user1 WITH ADMIN OPTION GRANTED BY regre
@@ -172,12 +172,16 @@ GRANT regress_priv_role TO regress_priv_user1 WITH ADMIN OPTION GRANTED BY regre
ERROR: permission denied to grant privileges as role "regress_priv_role"
DETAIL: The grantor must have the ADMIN option on role "regress_priv_role".
GRANT regress_priv_role TO regress_priv_user1 WITH ADMIN OPTION GRANTED BY CURRENT_ROLE;
@@ -1192,7 +1213,7 @@ index 5b9dba7b32..cc408dad42 100644
DROP ROLE regress_priv_role;
SET SESSION AUTHORIZATION regress_priv_user1;
SELECT session_user, current_user;
@@ -1776,7 +1780,7 @@ SELECT has_table_privilege('regress_priv_user1', 'atest4', 'SELECT WITH GRANT OP
@@ -1709,7 +1713,7 @@ SELECT has_table_privilege('regress_priv_user1', 'atest4', 'SELECT WITH GRANT OP
-- security-restricted operations
\c -
@@ -1201,7 +1222,7 @@ index 5b9dba7b32..cc408dad42 100644
-- Check that index expressions and predicates are run as the table's owner
-- A dummy index function checking current_user
CREATE FUNCTION sro_ifun(int) RETURNS int AS $$
@@ -2668,8 +2672,8 @@ drop cascades to function testns.priv_testagg(integer)
@@ -2601,8 +2605,8 @@ drop cascades to function testns.priv_testagg(integer)
drop cascades to function testns.priv_testproc(integer)
-- Change owner of the schema & and rename of new schema owner
\c -
@@ -1212,7 +1233,7 @@ index 5b9dba7b32..cc408dad42 100644
SET SESSION ROLE regress_schemauser1;
CREATE SCHEMA testns;
SELECT nspname, rolname FROM pg_namespace, pg_roles WHERE pg_namespace.nspname = 'testns' AND pg_namespace.nspowner = pg_roles.oid;
@@ -2792,7 +2796,7 @@ DROP USER regress_priv_user7;
@@ -2725,7 +2729,7 @@ DROP USER regress_priv_user7;
DROP USER regress_priv_user8; -- does not exist
ERROR: role "regress_priv_user8" does not exist
-- permissions with LOCK TABLE
@@ -1221,7 +1242,7 @@ index 5b9dba7b32..cc408dad42 100644
CREATE TABLE lock_table (a int);
-- LOCK TABLE and SELECT permission
GRANT SELECT ON lock_table TO regress_locktable_user;
@@ -2874,7 +2878,7 @@ DROP USER regress_locktable_user;
@@ -2807,7 +2811,7 @@ DROP USER regress_locktable_user;
-- pg_backend_memory_contexts.
-- switch to superuser
\c -
@@ -1230,7 +1251,7 @@ index 5b9dba7b32..cc408dad42 100644
SELECT has_table_privilege('regress_readallstats','pg_backend_memory_contexts','SELECT'); -- no
has_table_privilege
---------------------
@@ -2918,10 +2922,10 @@ RESET ROLE;
@@ -2851,10 +2855,10 @@ RESET ROLE;
-- clean up
DROP ROLE regress_readallstats;
-- test role grantor machinery
@@ -1245,7 +1266,7 @@ index 5b9dba7b32..cc408dad42 100644
GRANT regress_group TO regress_group_direct_manager WITH INHERIT FALSE, ADMIN TRUE;
GRANT regress_group_direct_manager TO regress_group_indirect_manager;
SET SESSION AUTHORIZATION regress_group_direct_manager;
@@ -2950,9 +2954,9 @@ DROP ROLE regress_group_direct_manager;
@@ -2883,9 +2887,9 @@ DROP ROLE regress_group_direct_manager;
DROP ROLE regress_group_indirect_manager;
DROP ROLE regress_group_member;
-- test SET and INHERIT options with object ownership changes
@@ -1792,7 +1813,7 @@ index 5e6969b173..2c4d52237f 100644
-- clean up roles
diff --git a/src/test/regress/expected/rowsecurity.out b/src/test/regress/expected/rowsecurity.out
index 218c0c2863..f7af0cfb12 100644
index 97ca9bf72c..b2a7a6f710 100644
--- a/src/test/regress/expected/rowsecurity.out
+++ b/src/test/regress/expected/rowsecurity.out
@@ -14,13 +14,13 @@ DROP ROLE IF EXISTS regress_rls_group2;
@@ -1896,19 +1917,6 @@ index b79fe9a1c0..e29fab88ab 100644
ALTER DEFAULT PRIVILEGES FOR ROLE regress_selinto_user
REVOKE INSERT ON TABLES FROM regress_selinto_user;
GRANT ALL ON SCHEMA selinto_schema TO public;
diff --git a/src/test/regress/expected/select_parallel.out b/src/test/regress/expected/select_parallel.out
index afc6ab08c2..dfcd891af3 100644
--- a/src/test/regress/expected/select_parallel.out
+++ b/src/test/regress/expected/select_parallel.out
@@ -1220,7 +1220,7 @@ SELECT 1 FROM tenk1_vw_sec
rollback;
-- test that function option SET ROLE works in parallel workers.
-create role regress_parallel_worker;
+create role regress_parallel_worker PASSWORD NEON_PASSWORD_PLACEHOLDER;
create function set_and_report_role() returns text as
$$ select current_setting('role') $$ language sql parallel safe
set role = regress_parallel_worker;
diff --git a/src/test/regress/expected/select_views.out b/src/test/regress/expected/select_views.out
index 1aeed8452b..7d9427d070 100644
--- a/src/test/regress/expected/select_views.out
@@ -2361,7 +2369,7 @@ index 6cb9c926c0..5e689e4062 100644
ALTER TABLE ptnowner1 OWNER TO regress_ptnowner;
ALTER TABLE ptnowner OWNER TO regress_ptnowner;
diff --git a/src/test/regress/sql/collate.icu.utf8.sql b/src/test/regress/sql/collate.icu.utf8.sql
index 8aa902d5ab..24bb823b86 100644
index 3db9e25913..c66d5aa2c2 100644
--- a/src/test/regress/sql/collate.icu.utf8.sql
+++ b/src/test/regress/sql/collate.icu.utf8.sql
@@ -353,7 +353,7 @@ reset enable_seqscan;
@@ -2524,7 +2532,7 @@ index 43d2e906dd..6c993d70f0 100644
-- An earlier bug (see commit b1ecb9b3fcf) could end up using a buffer from
-- the wrong partition. This test is *not* guaranteed to trigger that bug, but
diff --git a/src/test/regress/sql/copy2.sql b/src/test/regress/sql/copy2.sql
index cf3828c16e..cf3ca38175 100644
index d759635068..d58e50dcc5 100644
--- a/src/test/regress/sql/copy2.sql
+++ b/src/test/regress/sql/copy2.sql
@@ -365,8 +365,8 @@ copy check_con_tbl from stdin;
@@ -2766,7 +2774,7 @@ index 1b7064247a..be5b662ce1 100644
-- Cases where schema creation fails as objects are qualified with a schema
-- that does not match with what's expected.
diff --git a/src/test/regress/sql/create_view.sql b/src/test/regress/sql/create_view.sql
index ae6841308b..47bc792e30 100644
index 3a78be1b0c..617d2dc8d6 100644
--- a/src/test/regress/sql/create_view.sql
+++ b/src/test/regress/sql/create_view.sql
@@ -23,7 +23,8 @@ CREATE TABLE real_city (
@@ -2893,11 +2901,11 @@ index aa147b14a9..370e0dd570 100644
CREATE FOREIGN DATA WRAPPER dummy;
COMMENT ON FOREIGN DATA WRAPPER dummy IS 'useless';
diff --git a/src/test/regress/sql/foreign_key.sql b/src/test/regress/sql/foreign_key.sql
index 45c7a534cb..32dd26b8cd 100644
index 22e177f89b..7138d5e1d4 100644
--- a/src/test/regress/sql/foreign_key.sql
+++ b/src/test/regress/sql/foreign_key.sql
@@ -1435,7 +1435,7 @@ ALTER TABLE fk_partitioned_fk_6 ATTACH PARTITION fk_partitioned_pk_6 FOR VALUES
DROP TABLE fk_partitioned_pk_6, fk_partitioned_fk_6;
@@ -1418,7 +1418,7 @@ ALTER TABLE fk_partitioned_fk ATTACH PARTITION fk_partitioned_fk_2
-- leave these tables around intentionally
-- test the case when the referenced table is owned by a different user
-create role regress_other_partitioned_fk_owner;
@@ -2955,7 +2963,7 @@ index 527024f710..de49c0b85f 100644
-- the data in this file has a lot of duplicates in the index key
-- fields, leading to long bucket chains and lots of table expansion.
diff --git a/src/test/regress/sql/identity.sql b/src/test/regress/sql/identity.sql
index 7537258a75..9041e35e34 100644
index 91d2e443b4..241c93f373 100644
--- a/src/test/regress/sql/identity.sql
+++ b/src/test/regress/sql/identity.sql
@@ -287,7 +287,7 @@ ALTER TABLE itest7 ALTER COLUMN a RESTART;
@@ -2968,10 +2976,10 @@ index 7537258a75..9041e35e34 100644
GRANT SELECT, INSERT ON itest8 TO regress_identity_user1;
SET ROLE regress_identity_user1;
diff --git a/src/test/regress/sql/inherit.sql b/src/test/regress/sql/inherit.sql
index b5b554a125..109889ad24 100644
index fe699c54d5..bdd5993f45 100644
--- a/src/test/regress/sql/inherit.sql
+++ b/src/test/regress/sql/inherit.sql
@@ -958,7 +958,7 @@ create index on permtest_parent (left(c, 3));
@@ -950,7 +950,7 @@ create index on permtest_parent (left(c, 3));
insert into permtest_parent
select 1, 'a', left(fipshash(i::text), 5) from generate_series(0, 100) i;
analyze permtest_parent;
@@ -3173,7 +3181,7 @@ index 1a6c61f49d..1c31ac6a53 100644
-- Test generic object addressing/identification functions
CREATE SCHEMA addr_nsp;
diff --git a/src/test/regress/sql/password.sql b/src/test/regress/sql/password.sql
index 53e86b0b6c..0303fdfe96 100644
index 53e86b0b6c..f07cf1ec54 100644
--- a/src/test/regress/sql/password.sql
+++ b/src/test/regress/sql/password.sql
@@ -10,11 +10,11 @@ SET password_encryption = 'scram-sha-256'; -- ok
@@ -3192,61 +3200,25 @@ index 53e86b0b6c..0303fdfe96 100644
-- check list of created entries
--
@@ -42,26 +42,18 @@ ALTER ROLE regress_passwd2_new RENAME TO regress_passwd2;
@@ -42,14 +42,14 @@ ALTER ROLE regress_passwd2_new RENAME TO regress_passwd2;
SET password_encryption = 'md5';
-- encrypt with MD5
-ALTER ROLE regress_passwd2 PASSWORD 'foo';
--- already encrypted, use as they are
-ALTER ROLE regress_passwd1 PASSWORD 'md5cd3578025fe2c3d7ed1b9a9b26238b70';
-ALTER ROLE regress_passwd3 PASSWORD 'SCRAM-SHA-256$4096:VLK4RMaQLCvNtQ==$6YtlR4t69SguDiwFvbVgVZtuz6gpJQQqUMZ7IQJK5yI=:ps75jrHeYU4lXCcXI4O8oIdJ3eO8o2jirjruw9phBTo=';
+ALTER ROLE regress_passwd2 PASSWORD NEON_PASSWORD_PLACEHOLDER;
-- already encrypted, use as they are
ALTER ROLE regress_passwd1 PASSWORD 'md5cd3578025fe2c3d7ed1b9a9b26238b70';
ALTER ROLE regress_passwd3 PASSWORD 'SCRAM-SHA-256$4096:VLK4RMaQLCvNtQ==$6YtlR4t69SguDiwFvbVgVZtuz6gpJQQqUMZ7IQJK5yI=:ps75jrHeYU4lXCcXI4O8oIdJ3eO8o2jirjruw9phBTo=';
SET password_encryption = 'scram-sha-256';
-- create SCRAM secret
-ALTER ROLE regress_passwd4 PASSWORD 'foo';
--- already encrypted with MD5, use as it is
-CREATE ROLE regress_passwd5 PASSWORD 'md5e73a4b11df52a6068f8b39f90be36023';
+ALTER ROLE regress_passwd4 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+-- Neon does not support encrypted passwords, use unencrypted instead
+CREATE ROLE regress_passwd5 PASSWORD NEON_PASSWORD_PLACEHOLDER;
-- already encrypted with MD5, use as it is
CREATE ROLE regress_passwd5 PASSWORD 'md5e73a4b11df52a6068f8b39f90be36023';
--- This looks like a valid SCRAM-SHA-256 secret, but it is not
--- so it should be hashed with SCRAM-SHA-256.
-CREATE ROLE regress_passwd6 PASSWORD 'SCRAM-SHA-256$1234';
--- These may look like valid MD5 secrets, but they are not, so they
--- should be hashed with SCRAM-SHA-256.
--- trailing garbage at the end
-CREATE ROLE regress_passwd7 PASSWORD 'md5012345678901234567890123456789zz';
--- invalid length
-CREATE ROLE regress_passwd8 PASSWORD 'md501234567890123456789012345678901zz';
+-- Neon does not support encrypted passwords, use unencrypted instead
+CREATE ROLE regress_passwd6 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+CREATE ROLE regress_passwd7 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+CREATE ROLE regress_passwd8 PASSWORD NEON_PASSWORD_PLACEHOLDER;
-- Changing the SCRAM iteration count
SET scram_iterations = 1024;
@@ -78,13 +70,10 @@ ALTER ROLE regress_passwd_empty PASSWORD 'md585939a5ce845f1a1b620742e3c659e0a';
ALTER ROLE regress_passwd_empty PASSWORD 'SCRAM-SHA-256$4096:hpFyHTUsSWcR7O9P$LgZFIt6Oqdo27ZFKbZ2nV+vtnYM995pDh9ca6WSi120=:qVV5NeluNfUPkwm7Vqat25RjSPLkGeoZBQs6wVv+um4=';
SELECT rolpassword FROM pg_authid WHERE rolname='regress_passwd_empty';
--- Test with invalid stored and server keys.
---
--- The first is valid, to act as a control. The others have too long
--- stored/server keys. They will be re-hashed.
-CREATE ROLE regress_passwd_sha_len0 PASSWORD 'SCRAM-SHA-256$4096:A6xHKoH/494E941doaPOYg==$Ky+A30sewHIH3VHQLRN9vYsuzlgNyGNKCh37dy96Rqw=:COPdlNiIkrsacU5QoxydEuOH6e/KfiipeETb/bPw8ZI=';
-CREATE ROLE regress_passwd_sha_len1 PASSWORD 'SCRAM-SHA-256$4096:A6xHKoH/494E941doaPOYg==$Ky+A30sewHIH3VHQLRN9vYsuzlgNyGNKCh37dy96RqwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=:COPdlNiIkrsacU5QoxydEuOH6e/KfiipeETb/bPw8ZI=';
-CREATE ROLE regress_passwd_sha_len2 PASSWORD 'SCRAM-SHA-256$4096:A6xHKoH/494E941doaPOYg==$Ky+A30sewHIH3VHQLRN9vYsuzlgNyGNKCh37dy96Rqw=:COPdlNiIkrsacU5QoxydEuOH6e/KfiipeETb/bPw8ZIAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=';
+-- Neon does not support encrypted passwords, use unencrypted instead
+CREATE ROLE regress_passwd_sha_len0 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+CREATE ROLE regress_passwd_sha_len1 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+CREATE ROLE regress_passwd_sha_len2 PASSWORD NEON_PASSWORD_PLACEHOLDER;
-- Check that the invalid secrets were re-hashed. A re-hashed secret
-- should not contain the original salt.
diff --git a/src/test/regress/sql/privileges.sql b/src/test/regress/sql/privileges.sql
index 249df17a58..b258e7f26a 100644
index 3f68cafcd1..004b26831d 100644
--- a/src/test/regress/sql/privileges.sql
+++ b/src/test/regress/sql/privileges.sql
@@ -24,18 +24,18 @@ RESET client_min_messages;
@@ -3297,7 +3269,7 @@ index 249df17a58..b258e7f26a 100644
GRANT pg_read_all_data TO regress_priv_user6;
GRANT pg_write_all_data TO regress_priv_user7;
@@ -163,8 +163,8 @@ DROP USER regress_priv_user10;
@@ -130,8 +130,8 @@ DROP USER regress_priv_user10;
DROP USER regress_priv_user9;
DROP USER regress_priv_user8;
@@ -3308,7 +3280,7 @@ index 249df17a58..b258e7f26a 100644
ALTER GROUP regress_priv_group1 ADD USER regress_priv_user4;
@@ -1157,7 +1157,7 @@ SELECT has_table_privilege('regress_priv_user1', 'atest4', 'SELECT WITH GRANT OP
@@ -1124,7 +1124,7 @@ SELECT has_table_privilege('regress_priv_user1', 'atest4', 'SELECT WITH GRANT OP
-- security-restricted operations
\c -
@@ -3317,7 +3289,7 @@ index 249df17a58..b258e7f26a 100644
-- Check that index expressions and predicates are run as the table's owner
@@ -1653,8 +1653,8 @@ DROP SCHEMA testns CASCADE;
@@ -1620,8 +1620,8 @@ DROP SCHEMA testns CASCADE;
-- Change owner of the schema & and rename of new schema owner
\c -
@@ -3328,7 +3300,7 @@ index 249df17a58..b258e7f26a 100644
SET SESSION ROLE regress_schemauser1;
CREATE SCHEMA testns;
@@ -1748,7 +1748,7 @@ DROP USER regress_priv_user8; -- does not exist
@@ -1715,7 +1715,7 @@ DROP USER regress_priv_user8; -- does not exist
-- permissions with LOCK TABLE
@@ -3337,7 +3309,7 @@ index 249df17a58..b258e7f26a 100644
CREATE TABLE lock_table (a int);
-- LOCK TABLE and SELECT permission
@@ -1836,7 +1836,7 @@ DROP USER regress_locktable_user;
@@ -1803,7 +1803,7 @@ DROP USER regress_locktable_user;
-- switch to superuser
\c -
@@ -3346,7 +3318,7 @@ index 249df17a58..b258e7f26a 100644
SELECT has_table_privilege('regress_readallstats','pg_backend_memory_contexts','SELECT'); -- no
SELECT has_table_privilege('regress_readallstats','pg_shmem_allocations','SELECT'); -- no
@@ -1856,10 +1856,10 @@ RESET ROLE;
@@ -1823,10 +1823,10 @@ RESET ROLE;
DROP ROLE regress_readallstats;
-- test role grantor machinery
@@ -3361,7 +3333,7 @@ index 249df17a58..b258e7f26a 100644
GRANT regress_group TO regress_group_direct_manager WITH INHERIT FALSE, ADMIN TRUE;
GRANT regress_group_direct_manager TO regress_group_indirect_manager;
@@ -1881,9 +1881,9 @@ DROP ROLE regress_group_indirect_manager;
@@ -1848,9 +1848,9 @@ DROP ROLE regress_group_indirect_manager;
DROP ROLE regress_group_member;
-- test SET and INHERIT options with object ownership changes
@@ -3653,7 +3625,7 @@ index c961b2d730..0859b89c4f 100644
-- clean up roles
DROP ROLE regress_test_def_superuser;
diff --git a/src/test/regress/sql/rowsecurity.sql b/src/test/regress/sql/rowsecurity.sql
index d3bfd53e23..919ce1d0c6 100644
index dec7340538..cdbc03a5cc 100644
--- a/src/test/regress/sql/rowsecurity.sql
+++ b/src/test/regress/sql/rowsecurity.sql
@@ -20,13 +20,13 @@ DROP SCHEMA IF EXISTS regress_rls_schema CASCADE;
@@ -3729,19 +3701,6 @@ index 689c448cc2..223ceb1d75 100644
ALTER DEFAULT PRIVILEGES FOR ROLE regress_selinto_user
REVOKE INSERT ON TABLES FROM regress_selinto_user;
GRANT ALL ON SCHEMA selinto_schema TO public;
diff --git a/src/test/regress/sql/select_parallel.sql b/src/test/regress/sql/select_parallel.sql
index 33d78e16dc..cb193c9b27 100644
--- a/src/test/regress/sql/select_parallel.sql
+++ b/src/test/regress/sql/select_parallel.sql
@@ -464,7 +464,7 @@ SELECT 1 FROM tenk1_vw_sec
rollback;
-- test that function option SET ROLE works in parallel workers.
-create role regress_parallel_worker;
+create role regress_parallel_worker PASSWORD NEON_PASSWORD_PLACEHOLDER;
create function set_and_report_role() returns text as
$$ select current_setting('role') $$ language sql parallel safe
diff --git a/src/test/regress/sql/select_views.sql b/src/test/regress/sql/select_views.sql
index e742f13699..7bd0255df8 100644
--- a/src/test/regress/sql/select_views.sql

File diff suppressed because it is too large Load Diff

View File

@@ -1,242 +0,0 @@
diff --git a/contrib/amcheck/expected/check_heap.out b/contrib/amcheck/expected/check_heap.out
index 979e5e8..2375b45 100644
--- a/contrib/amcheck/expected/check_heap.out
+++ b/contrib/amcheck/expected/check_heap.out
@@ -80,12 +80,9 @@ INSERT INTO heaptest (a, b)
-- same transaction. The heaptest table is smaller than the default
-- wal_skip_threshold, so a wal_level=minimal commit reads the table into
-- shared_buffers. A transaction delays that and excludes any autovacuum.
-SET allow_in_place_tablespaces = true;
-CREATE TABLESPACE regress_test_stats_tblspc LOCATION '';
SELECT sum(reads) AS stats_bulkreads_before
FROM pg_stat_io WHERE context = 'bulkread' \gset
BEGIN;
-ALTER TABLE heaptest SET TABLESPACE regress_test_stats_tblspc;
-- Check that valid options are not rejected nor corruption reported
-- for a non-empty table
SELECT * FROM verify_heapam(relation := 'heaptest', skip := 'none');
@@ -118,14 +115,6 @@ SELECT pg_stat_force_next_flush();
(1 row)
-SELECT sum(reads) AS stats_bulkreads_after
- FROM pg_stat_io WHERE context = 'bulkread' \gset
-SELECT :stats_bulkreads_after > :stats_bulkreads_before;
- ?column?
-----------
- t
-(1 row)
-
CREATE ROLE regress_heaptest_role;
-- verify permissions are checked (error due to function not callable)
SET ROLE regress_heaptest_role;
@@ -233,7 +222,6 @@ ERROR: cannot check relation "test_foreign_table"
DETAIL: This operation is not supported for foreign tables.
-- cleanup
DROP TABLE heaptest;
-DROP TABLESPACE regress_test_stats_tblspc;
DROP TABLE test_partition;
DROP TABLE test_partitioned;
DROP OWNED BY regress_heaptest_role; -- permissions
diff --git a/contrib/amcheck/sql/check_heap.sql b/contrib/amcheck/sql/check_heap.sql
index 1745bae..3b429c3 100644
--- a/contrib/amcheck/sql/check_heap.sql
+++ b/contrib/amcheck/sql/check_heap.sql
@@ -40,12 +40,9 @@ INSERT INTO heaptest (a, b)
-- same transaction. The heaptest table is smaller than the default
-- wal_skip_threshold, so a wal_level=minimal commit reads the table into
-- shared_buffers. A transaction delays that and excludes any autovacuum.
-SET allow_in_place_tablespaces = true;
-CREATE TABLESPACE regress_test_stats_tblspc LOCATION '';
SELECT sum(reads) AS stats_bulkreads_before
FROM pg_stat_io WHERE context = 'bulkread' \gset
BEGIN;
-ALTER TABLE heaptest SET TABLESPACE regress_test_stats_tblspc;
-- Check that valid options are not rejected nor corruption reported
-- for a non-empty table
SELECT * FROM verify_heapam(relation := 'heaptest', skip := 'none');
@@ -58,9 +55,6 @@ COMMIT;
-- ALTER TABLE ... SET TABLESPACE ...
-- causing an additional bulkread, which should be reflected in pg_stat_io.
SELECT pg_stat_force_next_flush();
-SELECT sum(reads) AS stats_bulkreads_after
- FROM pg_stat_io WHERE context = 'bulkread' \gset
-SELECT :stats_bulkreads_after > :stats_bulkreads_before;
CREATE ROLE regress_heaptest_role;
@@ -140,7 +134,6 @@ SELECT * FROM verify_heapam('test_foreign_table',
-- cleanup
DROP TABLE heaptest;
-DROP TABLESPACE regress_test_stats_tblspc;
DROP TABLE test_partition;
DROP TABLE test_partitioned;
DROP OWNED BY regress_heaptest_role; -- permissions
diff --git a/contrib/citext/expected/create_index_acl.out b/contrib/citext/expected/create_index_acl.out
index 33be13a..70a406c 100644
--- a/contrib/citext/expected/create_index_acl.out
+++ b/contrib/citext/expected/create_index_acl.out
@@ -5,9 +5,6 @@
-- owner having as few applicable privileges as possible. (The privileges.sql
-- regress_sro_user tests look for the opposite defect; they confirm that
-- DefineIndex() uses the table owner userid where necessary.)
-SET allow_in_place_tablespaces = true;
-CREATE TABLESPACE regress_create_idx_tblspace LOCATION '';
-RESET allow_in_place_tablespaces;
BEGIN;
CREATE ROLE regress_minimal;
CREATE SCHEMA s;
@@ -49,11 +46,9 @@ ALTER TABLE s.x OWNER TO regress_minimal;
-- Empty-table DefineIndex()
CREATE UNIQUE INDEX u0rows ON s.x USING btree
((s.index_this_expr(y, s.const())) COLLATE s.coll s.citext_pattern_ops)
- TABLESPACE regress_create_idx_tblspace
WHERE s.index_row_if(y);
ALTER TABLE s.x ADD CONSTRAINT e0rows EXCLUDE USING btree
((s.index_this_expr(y, s.const())) COLLATE s.coll WITH s.=)
- USING INDEX TABLESPACE regress_create_idx_tblspace
WHERE (s.index_row_if(y));
-- Make the table nonempty.
INSERT INTO s.x VALUES ('foo'), ('bar');
@@ -66,11 +61,9 @@ RESET search_path;
GRANT EXECUTE ON FUNCTION s.index_this_expr TO regress_minimal;
CREATE UNIQUE INDEX u2rows ON s.x USING btree
((s.index_this_expr(y, s.const())) COLLATE s.coll s.citext_pattern_ops)
- TABLESPACE regress_create_idx_tblspace
WHERE s.index_row_if(y);
ALTER TABLE s.x ADD CONSTRAINT e2rows EXCLUDE USING btree
((s.index_this_expr(y, s.const())) COLLATE s.coll WITH s.=)
- USING INDEX TABLESPACE regress_create_idx_tblspace
WHERE (s.index_row_if(y));
-- Shall not find s.coll via search_path, despite the s.const->public.setter
-- call having set search_path=s during expression planning. Suppress the
@@ -78,9 +71,7 @@ ALTER TABLE s.x ADD CONSTRAINT e2rows EXCLUDE USING btree
\set VERBOSITY sqlstate
ALTER TABLE s.x ADD CONSTRAINT underqualified EXCLUDE USING btree
((s.index_this_expr(y, s.const())) COLLATE coll WITH s.=)
- USING INDEX TABLESPACE regress_create_idx_tblspace
WHERE (s.index_row_if(y));
ERROR: 42704
\set VERBOSITY default
ROLLBACK;
-DROP TABLESPACE regress_create_idx_tblspace;
diff --git a/contrib/citext/sql/create_index_acl.sql b/contrib/citext/sql/create_index_acl.sql
index 10b5225..ae442e1 100644
--- a/contrib/citext/sql/create_index_acl.sql
+++ b/contrib/citext/sql/create_index_acl.sql
@@ -6,10 +6,6 @@
-- regress_sro_user tests look for the opposite defect; they confirm that
-- DefineIndex() uses the table owner userid where necessary.)
-SET allow_in_place_tablespaces = true;
-CREATE TABLESPACE regress_create_idx_tblspace LOCATION '';
-RESET allow_in_place_tablespaces;
-
BEGIN;
CREATE ROLE regress_minimal;
CREATE SCHEMA s;
@@ -51,11 +47,9 @@ ALTER TABLE s.x OWNER TO regress_minimal;
-- Empty-table DefineIndex()
CREATE UNIQUE INDEX u0rows ON s.x USING btree
((s.index_this_expr(y, s.const())) COLLATE s.coll s.citext_pattern_ops)
- TABLESPACE regress_create_idx_tblspace
WHERE s.index_row_if(y);
ALTER TABLE s.x ADD CONSTRAINT e0rows EXCLUDE USING btree
((s.index_this_expr(y, s.const())) COLLATE s.coll WITH s.=)
- USING INDEX TABLESPACE regress_create_idx_tblspace
WHERE (s.index_row_if(y));
-- Make the table nonempty.
INSERT INTO s.x VALUES ('foo'), ('bar');
@@ -68,11 +62,9 @@ RESET search_path;
GRANT EXECUTE ON FUNCTION s.index_this_expr TO regress_minimal;
CREATE UNIQUE INDEX u2rows ON s.x USING btree
((s.index_this_expr(y, s.const())) COLLATE s.coll s.citext_pattern_ops)
- TABLESPACE regress_create_idx_tblspace
WHERE s.index_row_if(y);
ALTER TABLE s.x ADD CONSTRAINT e2rows EXCLUDE USING btree
((s.index_this_expr(y, s.const())) COLLATE s.coll WITH s.=)
- USING INDEX TABLESPACE regress_create_idx_tblspace
WHERE (s.index_row_if(y));
-- Shall not find s.coll via search_path, despite the s.const->public.setter
-- call having set search_path=s during expression planning. Suppress the
@@ -80,9 +72,7 @@ ALTER TABLE s.x ADD CONSTRAINT e2rows EXCLUDE USING btree
\set VERBOSITY sqlstate
ALTER TABLE s.x ADD CONSTRAINT underqualified EXCLUDE USING btree
((s.index_this_expr(y, s.const())) COLLATE coll WITH s.=)
- USING INDEX TABLESPACE regress_create_idx_tblspace
WHERE (s.index_row_if(y));
\set VERBOSITY default
ROLLBACK;
-DROP TABLESPACE regress_create_idx_tblspace;
diff --git a/contrib/file_fdw/expected/file_fdw.out b/contrib/file_fdw/expected/file_fdw.out
index 72304e0..ebe131b 100644
--- a/contrib/file_fdw/expected/file_fdw.out
+++ b/contrib/file_fdw/expected/file_fdw.out
@@ -4,6 +4,7 @@
-- directory paths are passed to us in environment variables
\getenv abs_srcdir PG_ABS_SRCDIR
-- Clean up in case a prior regression run failed
+SET compute_query_id TO 'off';
SET client_min_messages TO 'warning';
DROP ROLE IF EXISTS regress_file_fdw_superuser, regress_file_fdw_user, regress_no_priv_user;
RESET client_min_messages;
diff --git a/contrib/file_fdw/sql/file_fdw.sql b/contrib/file_fdw/sql/file_fdw.sql
index f0548e1..848a08c 100644
--- a/contrib/file_fdw/sql/file_fdw.sql
+++ b/contrib/file_fdw/sql/file_fdw.sql
@@ -6,6 +6,7 @@
\getenv abs_srcdir PG_ABS_SRCDIR
-- Clean up in case a prior regression run failed
+SET compute_query_id TO 'off';
SET client_min_messages TO 'warning';
DROP ROLE IF EXISTS regress_file_fdw_superuser, regress_file_fdw_user, regress_no_priv_user;
RESET client_min_messages;
diff --git a/contrib/pageinspect/expected/gist.out b/contrib/pageinspect/expected/gist.out
index d1adbab..38b52ac 100644
--- a/contrib/pageinspect/expected/gist.out
+++ b/contrib/pageinspect/expected/gist.out
@@ -10,25 +10,6 @@ BEGIN;
CREATE TABLE test_gist AS SELECT point(i,i) p, i::text t FROM
generate_series(1,1000) i;
CREATE INDEX test_gist_idx ON test_gist USING gist (p);
--- Page 0 is the root, the rest are leaf pages
-SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist_idx', 0));
- lsn | nsn | rightlink | flags
------+-----+------------+-------
- 0/1 | 0/0 | 4294967295 | {}
-(1 row)
-
-SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist_idx', 1));
- lsn | nsn | rightlink | flags
------+-----+------------+--------
- 0/1 | 0/0 | 4294967295 | {leaf}
-(1 row)
-
-SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist_idx', 2));
- lsn | nsn | rightlink | flags
------+-----+-----------+--------
- 0/1 | 0/0 | 1 | {leaf}
-(1 row)
-
COMMIT;
SELECT * FROM gist_page_items(get_raw_page('test_gist_idx', 0), 'test_gist_idx');
itemoffset | ctid | itemlen | dead | keys
diff --git a/contrib/pageinspect/sql/gist.sql b/contrib/pageinspect/sql/gist.sql
index d263542..607992f 100644
--- a/contrib/pageinspect/sql/gist.sql
+++ b/contrib/pageinspect/sql/gist.sql
@@ -12,11 +12,6 @@ CREATE TABLE test_gist AS SELECT point(i,i) p, i::text t FROM
generate_series(1,1000) i;
CREATE INDEX test_gist_idx ON test_gist USING gist (p);
--- Page 0 is the root, the rest are leaf pages
-SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist_idx', 0));
-SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist_idx', 1));
-SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist_idx', 2));
-
COMMIT;
SELECT * FROM gist_page_items(get_raw_page('test_gist_idx', 0), 'test_gist_idx');

View File

@@ -1,196 +0,0 @@
diff --git a/contrib/amcheck/expected/check_heap.out b/contrib/amcheck/expected/check_heap.out
index 979e5e8..2375b45 100644
--- a/contrib/amcheck/expected/check_heap.out
+++ b/contrib/amcheck/expected/check_heap.out
@@ -80,12 +80,9 @@ INSERT INTO heaptest (a, b)
-- same transaction. The heaptest table is smaller than the default
-- wal_skip_threshold, so a wal_level=minimal commit reads the table into
-- shared_buffers. A transaction delays that and excludes any autovacuum.
-SET allow_in_place_tablespaces = true;
-CREATE TABLESPACE regress_test_stats_tblspc LOCATION '';
SELECT sum(reads) AS stats_bulkreads_before
FROM pg_stat_io WHERE context = 'bulkread' \gset
BEGIN;
-ALTER TABLE heaptest SET TABLESPACE regress_test_stats_tblspc;
-- Check that valid options are not rejected nor corruption reported
-- for a non-empty table
SELECT * FROM verify_heapam(relation := 'heaptest', skip := 'none');
@@ -118,14 +115,6 @@ SELECT pg_stat_force_next_flush();
(1 row)
-SELECT sum(reads) AS stats_bulkreads_after
- FROM pg_stat_io WHERE context = 'bulkread' \gset
-SELECT :stats_bulkreads_after > :stats_bulkreads_before;
- ?column?
-----------
- t
-(1 row)
-
CREATE ROLE regress_heaptest_role;
-- verify permissions are checked (error due to function not callable)
SET ROLE regress_heaptest_role;
@@ -233,7 +222,6 @@ ERROR: cannot check relation "test_foreign_table"
DETAIL: This operation is not supported for foreign tables.
-- cleanup
DROP TABLE heaptest;
-DROP TABLESPACE regress_test_stats_tblspc;
DROP TABLE test_partition;
DROP TABLE test_partitioned;
DROP OWNED BY regress_heaptest_role; -- permissions
diff --git a/contrib/amcheck/sql/check_heap.sql b/contrib/amcheck/sql/check_heap.sql
index 1745bae..3b429c3 100644
--- a/contrib/amcheck/sql/check_heap.sql
+++ b/contrib/amcheck/sql/check_heap.sql
@@ -40,12 +40,9 @@ INSERT INTO heaptest (a, b)
-- same transaction. The heaptest table is smaller than the default
-- wal_skip_threshold, so a wal_level=minimal commit reads the table into
-- shared_buffers. A transaction delays that and excludes any autovacuum.
-SET allow_in_place_tablespaces = true;
-CREATE TABLESPACE regress_test_stats_tblspc LOCATION '';
SELECT sum(reads) AS stats_bulkreads_before
FROM pg_stat_io WHERE context = 'bulkread' \gset
BEGIN;
-ALTER TABLE heaptest SET TABLESPACE regress_test_stats_tblspc;
-- Check that valid options are not rejected nor corruption reported
-- for a non-empty table
SELECT * FROM verify_heapam(relation := 'heaptest', skip := 'none');
@@ -58,9 +55,6 @@ COMMIT;
-- ALTER TABLE ... SET TABLESPACE ...
-- causing an additional bulkread, which should be reflected in pg_stat_io.
SELECT pg_stat_force_next_flush();
-SELECT sum(reads) AS stats_bulkreads_after
- FROM pg_stat_io WHERE context = 'bulkread' \gset
-SELECT :stats_bulkreads_after > :stats_bulkreads_before;
CREATE ROLE regress_heaptest_role;
@@ -140,7 +134,6 @@ SELECT * FROM verify_heapam('test_foreign_table',
-- cleanup
DROP TABLE heaptest;
-DROP TABLESPACE regress_test_stats_tblspc;
DROP TABLE test_partition;
DROP TABLE test_partitioned;
DROP OWNED BY regress_heaptest_role; -- permissions
diff --git a/contrib/citext/expected/create_index_acl.out b/contrib/citext/expected/create_index_acl.out
index 33be13a..70a406c 100644
--- a/contrib/citext/expected/create_index_acl.out
+++ b/contrib/citext/expected/create_index_acl.out
@@ -5,9 +5,6 @@
-- owner having as few applicable privileges as possible. (The privileges.sql
-- regress_sro_user tests look for the opposite defect; they confirm that
-- DefineIndex() uses the table owner userid where necessary.)
-SET allow_in_place_tablespaces = true;
-CREATE TABLESPACE regress_create_idx_tblspace LOCATION '';
-RESET allow_in_place_tablespaces;
BEGIN;
CREATE ROLE regress_minimal;
CREATE SCHEMA s;
@@ -49,11 +46,9 @@ ALTER TABLE s.x OWNER TO regress_minimal;
-- Empty-table DefineIndex()
CREATE UNIQUE INDEX u0rows ON s.x USING btree
((s.index_this_expr(y, s.const())) COLLATE s.coll s.citext_pattern_ops)
- TABLESPACE regress_create_idx_tblspace
WHERE s.index_row_if(y);
ALTER TABLE s.x ADD CONSTRAINT e0rows EXCLUDE USING btree
((s.index_this_expr(y, s.const())) COLLATE s.coll WITH s.=)
- USING INDEX TABLESPACE regress_create_idx_tblspace
WHERE (s.index_row_if(y));
-- Make the table nonempty.
INSERT INTO s.x VALUES ('foo'), ('bar');
@@ -66,11 +61,9 @@ RESET search_path;
GRANT EXECUTE ON FUNCTION s.index_this_expr TO regress_minimal;
CREATE UNIQUE INDEX u2rows ON s.x USING btree
((s.index_this_expr(y, s.const())) COLLATE s.coll s.citext_pattern_ops)
- TABLESPACE regress_create_idx_tblspace
WHERE s.index_row_if(y);
ALTER TABLE s.x ADD CONSTRAINT e2rows EXCLUDE USING btree
((s.index_this_expr(y, s.const())) COLLATE s.coll WITH s.=)
- USING INDEX TABLESPACE regress_create_idx_tblspace
WHERE (s.index_row_if(y));
-- Shall not find s.coll via search_path, despite the s.const->public.setter
-- call having set search_path=s during expression planning. Suppress the
@@ -78,9 +71,7 @@ ALTER TABLE s.x ADD CONSTRAINT e2rows EXCLUDE USING btree
\set VERBOSITY sqlstate
ALTER TABLE s.x ADD CONSTRAINT underqualified EXCLUDE USING btree
((s.index_this_expr(y, s.const())) COLLATE coll WITH s.=)
- USING INDEX TABLESPACE regress_create_idx_tblspace
WHERE (s.index_row_if(y));
ERROR: 42704
\set VERBOSITY default
ROLLBACK;
-DROP TABLESPACE regress_create_idx_tblspace;
diff --git a/contrib/citext/sql/create_index_acl.sql b/contrib/citext/sql/create_index_acl.sql
index 10b5225..ae442e1 100644
--- a/contrib/citext/sql/create_index_acl.sql
+++ b/contrib/citext/sql/create_index_acl.sql
@@ -6,10 +6,6 @@
-- regress_sro_user tests look for the opposite defect; they confirm that
-- DefineIndex() uses the table owner userid where necessary.)
-SET allow_in_place_tablespaces = true;
-CREATE TABLESPACE regress_create_idx_tblspace LOCATION '';
-RESET allow_in_place_tablespaces;
-
BEGIN;
CREATE ROLE regress_minimal;
CREATE SCHEMA s;
@@ -51,11 +47,9 @@ ALTER TABLE s.x OWNER TO regress_minimal;
-- Empty-table DefineIndex()
CREATE UNIQUE INDEX u0rows ON s.x USING btree
((s.index_this_expr(y, s.const())) COLLATE s.coll s.citext_pattern_ops)
- TABLESPACE regress_create_idx_tblspace
WHERE s.index_row_if(y);
ALTER TABLE s.x ADD CONSTRAINT e0rows EXCLUDE USING btree
((s.index_this_expr(y, s.const())) COLLATE s.coll WITH s.=)
- USING INDEX TABLESPACE regress_create_idx_tblspace
WHERE (s.index_row_if(y));
-- Make the table nonempty.
INSERT INTO s.x VALUES ('foo'), ('bar');
@@ -68,11 +62,9 @@ RESET search_path;
GRANT EXECUTE ON FUNCTION s.index_this_expr TO regress_minimal;
CREATE UNIQUE INDEX u2rows ON s.x USING btree
((s.index_this_expr(y, s.const())) COLLATE s.coll s.citext_pattern_ops)
- TABLESPACE regress_create_idx_tblspace
WHERE s.index_row_if(y);
ALTER TABLE s.x ADD CONSTRAINT e2rows EXCLUDE USING btree
((s.index_this_expr(y, s.const())) COLLATE s.coll WITH s.=)
- USING INDEX TABLESPACE regress_create_idx_tblspace
WHERE (s.index_row_if(y));
-- Shall not find s.coll via search_path, despite the s.const->public.setter
-- call having set search_path=s during expression planning. Suppress the
@@ -80,9 +72,7 @@ ALTER TABLE s.x ADD CONSTRAINT e2rows EXCLUDE USING btree
\set VERBOSITY sqlstate
ALTER TABLE s.x ADD CONSTRAINT underqualified EXCLUDE USING btree
((s.index_this_expr(y, s.const())) COLLATE coll WITH s.=)
- USING INDEX TABLESPACE regress_create_idx_tblspace
WHERE (s.index_row_if(y));
\set VERBOSITY default
ROLLBACK;
-DROP TABLESPACE regress_create_idx_tblspace;
diff --git a/contrib/file_fdw/expected/file_fdw.out b/contrib/file_fdw/expected/file_fdw.out
index 86c148a..81bdb2c 100644
--- a/contrib/file_fdw/expected/file_fdw.out
+++ b/contrib/file_fdw/expected/file_fdw.out
@@ -4,6 +4,7 @@
-- directory paths are passed to us in environment variables
\getenv abs_srcdir PG_ABS_SRCDIR
-- Clean up in case a prior regression run failed
+SET compute_query_id TO 'off';
SET client_min_messages TO 'warning';
DROP ROLE IF EXISTS regress_file_fdw_superuser, regress_file_fdw_user, regress_no_priv_user;
RESET client_min_messages;
diff --git a/contrib/file_fdw/sql/file_fdw.sql b/contrib/file_fdw/sql/file_fdw.sql
index f0548e1..848a08c 100644
--- a/contrib/file_fdw/sql/file_fdw.sql
+++ b/contrib/file_fdw/sql/file_fdw.sql
@@ -6,6 +6,7 @@
\getenv abs_srcdir PG_ABS_SRCDIR
-- Clean up in case a prior regression run failed
+SET compute_query_id TO 'off';
SET client_min_messages TO 'warning';
DROP ROLE IF EXISTS regress_file_fdw_superuser, regress_file_fdw_user, regress_no_priv_user;
RESET client_min_messages;

View File

@@ -1,19 +0,0 @@
commit ec6a491d126882966a696f9ad5d3698935361d55
Author: Alexey Masterov <alexeymasterov@neon.tech>
Date: Tue Dec 17 10:25:00 2024 +0100
Changes required to run tests on Neon
diff --git a/test/expected/permissions_functions.out b/test/expected/permissions_functions.out
index 1e9fbc2..94cbe25 100644
--- a/test/expected/permissions_functions.out
+++ b/test/expected/permissions_functions.out
@@ -64,7 +64,7 @@ begin;
select current_user;
current_user
--------------
- postgres
+ cloud_admin
(1 row)
-- revoke default access from the public role for new functions

View File

@@ -1,174 +0,0 @@
diff --git a/expected/ut-A.out b/expected/ut-A.out
index e7d68a1..65a056c 100644
--- a/expected/ut-A.out
+++ b/expected/ut-A.out
@@ -9,13 +9,16 @@ SET search_path TO public;
----
-- No.A-1-1-3
CREATE EXTENSION pg_hint_plan;
+LOG: Sending request to compute_ctl: http://localhost:3080/extension_server/pg_hint_plan
-- No.A-1-2-3
DROP EXTENSION pg_hint_plan;
-- No.A-1-1-4
CREATE SCHEMA other_schema;
CREATE EXTENSION pg_hint_plan SCHEMA other_schema;
+LOG: Sending request to compute_ctl: http://localhost:3080/extension_server/pg_hint_plan
ERROR: extension "pg_hint_plan" must be installed in schema "hint_plan"
CREATE EXTENSION pg_hint_plan;
+LOG: Sending request to compute_ctl: http://localhost:3080/extension_server/pg_hint_plan
DROP SCHEMA other_schema;
----
---- No. A-5-1 comment pattern
diff --git a/expected/ut-J.out b/expected/ut-J.out
index 2fa3c70..314e929 100644
--- a/expected/ut-J.out
+++ b/expected/ut-J.out
@@ -789,38 +789,6 @@ NestLoop(st1 st2)
MergeJoin(t1 t2)
not used hint:
duplication hint:
-error hint:
-
-LOG: pg_hint_plan:
-used hint:
-not used hint:
-NestLoop(st1 st2)
-MergeJoin(t1 t2)
-duplication hint:
-error hint:
-
-LOG: pg_hint_plan:
-used hint:
-not used hint:
-NestLoop(st1 st2)
-MergeJoin(t1 t2)
-duplication hint:
-error hint:
-
-LOG: pg_hint_plan:
-used hint:
-not used hint:
-NestLoop(st1 st2)
-MergeJoin(t1 t2)
-duplication hint:
-error hint:
-
-LOG: pg_hint_plan:
-used hint:
-not used hint:
-NestLoop(st1 st2)
-MergeJoin(t1 t2)
-duplication hint:
error hint:
explain_filter
diff --git a/expected/ut-S.out b/expected/ut-S.out
index 0bfcfb8..e75f581 100644
--- a/expected/ut-S.out
+++ b/expected/ut-S.out
@@ -4415,34 +4415,6 @@ used hint:
IndexScan(ti1 ti1_pred)
not used hint:
duplication hint:
-error hint:
-
-LOG: pg_hint_plan:
-used hint:
-not used hint:
-IndexScan(ti1 ti1_pred)
-duplication hint:
-error hint:
-
-LOG: pg_hint_plan:
-used hint:
-not used hint:
-IndexScan(ti1 ti1_pred)
-duplication hint:
-error hint:
-
-LOG: pg_hint_plan:
-used hint:
-not used hint:
-IndexScan(ti1 ti1_pred)
-duplication hint:
-error hint:
-
-LOG: pg_hint_plan:
-used hint:
-not used hint:
-IndexScan(ti1 ti1_pred)
-duplication hint:
error hint:
explain_filter
diff --git a/expected/ut-W.out b/expected/ut-W.out
index a09bd34..0ad227c 100644
--- a/expected/ut-W.out
+++ b/expected/ut-W.out
@@ -1341,54 +1341,6 @@ IndexScan(ft1)
IndexScan(t)
Parallel(s1 3 hard)
duplication hint:
-error hint:
-
-LOG: pg_hint_plan:
-used hint:
-not used hint:
-IndexScan(*VALUES*)
-SeqScan(cte1)
-IndexScan(ft1)
-IndexScan(t)
-Parallel(p1 5 hard)
-Parallel(s1 3 hard)
-duplication hint:
-error hint:
-
-LOG: pg_hint_plan:
-used hint:
-not used hint:
-IndexScan(*VALUES*)
-SeqScan(cte1)
-IndexScan(ft1)
-IndexScan(t)
-Parallel(p1 5 hard)
-Parallel(s1 3 hard)
-duplication hint:
-error hint:
-
-LOG: pg_hint_plan:
-used hint:
-not used hint:
-IndexScan(*VALUES*)
-SeqScan(cte1)
-IndexScan(ft1)
-IndexScan(t)
-Parallel(p1 5 hard)
-Parallel(s1 3 hard)
-duplication hint:
-error hint:
-
-LOG: pg_hint_plan:
-used hint:
-not used hint:
-IndexScan(*VALUES*)
-SeqScan(cte1)
-IndexScan(ft1)
-IndexScan(t)
-Parallel(p1 5 hard)
-Parallel(s1 3 hard)
-duplication hint:
error hint:
explain_filter
diff --git a/expected/ut-fdw.out b/expected/ut-fdw.out
index 017fa4b..98d989b 100644
--- a/expected/ut-fdw.out
+++ b/expected/ut-fdw.out
@@ -7,6 +7,7 @@ SET pg_hint_plan.debug_print TO on;
SET client_min_messages TO LOG;
SET pg_hint_plan.enable_hint TO on;
CREATE EXTENSION file_fdw;
+LOG: Sending request to compute_ctl: http://localhost:3080/extension_server/file_fdw
CREATE SERVER file_server FOREIGN DATA WRAPPER file_fdw;
CREATE USER MAPPING FOR PUBLIC SERVER file_server;
CREATE FOREIGN TABLE ft1 (id int, val int) SERVER file_server OPTIONS (format 'csv', filename :'filename');

View File

@@ -1,24 +1,8 @@
diff --git a/Makefile b/Makefile
index 7a4b88c..56678af 100644
--- a/Makefile
+++ b/Makefile
@@ -3,7 +3,10 @@ EXTVERSION = 0.8.0
MODULE_big = vector
DATA = $(wildcard sql/*--*--*.sql)
-DATA_built = sql/$(EXTENSION)--$(EXTVERSION).sql
+# This change is needed to install different per-version SQL files
+# like pgvector--0.8.0.sql and pgvector--0.7.4.sql
+# The corresponding file is downloaded during the Docker image build process
+DATA_built = sql/$(EXTENSION)--$(EXTVERSION).sql sql/vector--0.7.4.sql
OBJS = src/bitutils.o src/bitvec.o src/halfutils.o src/halfvec.o src/hnsw.o src/hnswbuild.o src/hnswinsert.o src/hnswscan.o src/hnswutils.o src/hnswvacuum.o src/ivfbuild.o src/ivfflat.o src/ivfinsert.o src/ivfkmeans.o src/ivfscan.o src/ivfutils.o src/ivfvacuum.o src/sparsevec.o src/vector.o
HEADERS = src/halfvec.h src/sparsevec.h src/vector.h
diff --git a/src/hnswbuild.c b/src/hnswbuild.c
index b667478..fc1897c 100644
index dcfb2bd..d5189ee 100644
--- a/src/hnswbuild.c
+++ b/src/hnswbuild.c
@@ -843,9 +843,17 @@ HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc)
@@ -860,9 +860,17 @@ HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc)
hnswarea = shm_toc_lookup(toc, PARALLEL_KEY_HNSW_AREA, false);
@@ -36,7 +20,7 @@ index b667478..fc1897c 100644
/* Close relations within worker */
index_close(indexRel, indexLockmode);
table_close(heapRel, heapLockmode);
@@ -1100,12 +1108,38 @@ BuildIndex(Relation heap, Relation index, IndexInfo *indexInfo,
@@ -1117,12 +1125,38 @@ BuildIndex(Relation heap, Relation index, IndexInfo *indexInfo,
SeedRandom(42);
#endif

View File

@@ -1,42 +0,0 @@
commit 46b38d3e46f9cd6c70d9b189dd6ff4abaa17cf5e
Author: Alexander Bayandin <alexander@neon.tech>
Date: Sat Nov 30 18:29:32 2024 +0000
Fix v8 9.7.37 compilation on Debian 12
diff --git a/patches/code/84cf3230a9680aac3b73c410c2b758760b6d3066.patch b/patches/code/84cf3230a9680aac3b73c410c2b758760b6d3066.patch
new file mode 100644
index 0000000..f0a5dc7
--- /dev/null
+++ b/patches/code/84cf3230a9680aac3b73c410c2b758760b6d3066.patch
@@ -0,0 +1,30 @@
+From 84cf3230a9680aac3b73c410c2b758760b6d3066 Mon Sep 17 00:00:00 2001
+From: Michael Lippautz <mlippautz@chromium.org>
+Date: Thu, 27 Jan 2022 14:14:11 +0100
+Subject: [PATCH] cppgc: Fix include
+
+Add <utility> to cover for std::exchange.
+
+Bug: v8:12585
+Change-Id: Ida65144e93e466be8914527d0e646f348c136bcb
+Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3420309
+Auto-Submit: Michael Lippautz <mlippautz@chromium.org>
+Reviewed-by: Omer Katz <omerkatz@chromium.org>
+Commit-Queue: Michael Lippautz <mlippautz@chromium.org>
+Cr-Commit-Position: refs/heads/main@{#78820}
+---
+ src/heap/cppgc/prefinalizer-handler.h | 1 +
+ 1 file changed, 1 insertion(+)
+
+diff --git a/src/heap/cppgc/prefinalizer-handler.h b/src/heap/cppgc/prefinalizer-handler.h
+index bc17c99b1838..c82c91ff5a45 100644
+--- a/src/heap/cppgc/prefinalizer-handler.h
++++ b/src/heap/cppgc/prefinalizer-handler.h
+@@ -5,6 +5,7 @@
+ #ifndef V8_HEAP_CPPGC_PREFINALIZER_HANDLER_H_
+ #define V8_HEAP_CPPGC_PREFINALIZER_HANDLER_H_
+
++#include <utility>
+ #include <vector>
+
+ #include "include/cppgc/prefinalizer.h"

View File

@@ -27,10 +27,6 @@ commands:
user: nobody
sysvInitAction: respawn
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
shell: '/bin/pgbouncer_exporter --pgBouncer.connectionString="postgres:///pgbouncer?host=/tmp&port=6432&dbname=pgbouncer&user=pgbouncer"'
- name: sql-exporter
user: nobody
sysvInitAction: respawn

View File

@@ -27,10 +27,6 @@ commands:
user: nobody
sysvInitAction: respawn
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
shell: '/bin/pgbouncer_exporter --pgBouncer.connectionString="postgres:///pgbouncer?host=/tmp&port=6432&dbname=pgbouncer&user=pgbouncer"'
- name: sql-exporter
user: nobody
sysvInitAction: respawn

View File

@@ -7,23 +7,17 @@ license.workspace = true
[features]
default = []
# Enables test specific features.
testing = ["fail/failpoints"]
testing = []
[dependencies]
base64.workspace = true
aws-config.workspace = true
aws-sdk-s3.workspace = true
aws-sdk-kms.workspace = true
anyhow.workspace = true
axum = { workspace = true, features = [] }
camino.workspace = true
chrono.workspace = true
cfg-if.workspace = true
clap.workspace = true
fail.workspace = true
flate2.workspace = true
futures.workspace = true
http.workspace = true
hyper0 = { workspace = true, features = ["full"] }
metrics.workspace = true
nix.workspace = true
notify.workspace = true
@@ -33,13 +27,9 @@ opentelemetry.workspace = true
opentelemetry_sdk.workspace = true
postgres.workspace = true
regex.workspace = true
serde.workspace = true
serde_with.workspace = true
serde_json.workspace = true
signal-hook.workspace = true
tar.workspace = true
tower.workspace = true
tower-http.workspace = true
reqwest = { workspace = true, features = ["json"] }
tokio = { workspace = true, features = ["rt", "rt-multi-thread"] }
tokio-postgres.workspace = true
@@ -51,10 +41,8 @@ tracing-subscriber.workspace = true
tracing-utils.workspace = true
thiserror.workspace = true
url.workspace = true
uuid.workspace = true
prometheus.workspace = true
postgres_initdb.workspace = true
compute_api.workspace = true
utils.workspace = true
workspace_hack.workspace = true

View File

@@ -34,18 +34,16 @@
//! -r http://pg-ext-s3-gateway \
//! ```
use std::collections::HashMap;
use std::ffi::OsString;
use std::fs::File;
use std::path::Path;
use std::process::exit;
use std::str::FromStr;
use std::sync::atomic::Ordering;
use std::sync::{mpsc, Arc, Condvar, Mutex, RwLock};
use std::{thread, time::Duration};
use anyhow::{Context, Result};
use chrono::Utc;
use clap::Parser;
use clap::Arg;
use compute_tools::disk_quota::set_disk_quota;
use compute_tools::lsn_lease::launch_lsn_lease_bg_task_for_static;
use signal_hook::consts::{SIGQUIT, SIGTERM};
@@ -60,89 +58,21 @@ use compute_tools::compute::{
forward_termination_signal, ComputeNode, ComputeState, ParsedSpec, PG_PID,
};
use compute_tools::configurator::launch_configurator;
use compute_tools::extension_server::get_pg_version_string;
use compute_tools::http::launch_http_server;
use compute_tools::extension_server::get_pg_version;
use compute_tools::http::api::launch_http_server;
use compute_tools::logger::*;
use compute_tools::monitor::launch_monitor;
use compute_tools::params::*;
use compute_tools::spec::*;
use compute_tools::swap::resize_swap;
use rlimit::{setrlimit, Resource};
use utils::failpoint_support;
// this is an arbitrary build tag. Fine as a default / for testing purposes
// in-case of not-set environment var
const BUILD_TAG_DEFAULT: &str = "latest";
// Compatibility hack: if the control plane specified any remote-ext-config
// use the default value for extension storage proxy gateway.
// Remove this once the control plane is updated to pass the gateway URL
fn parse_remote_ext_config(arg: &str) -> Result<String> {
if arg.starts_with("http") {
Ok(arg.trim_end_matches('/').to_string())
} else {
Ok("http://pg-ext-s3-gateway".to_string())
}
}
#[derive(Parser)]
#[command(rename_all = "kebab-case")]
struct Cli {
#[arg(short = 'b', long, default_value = "postgres", env = "POSTGRES_PATH")]
pub pgbin: String,
#[arg(short = 'r', long, value_parser = parse_remote_ext_config)]
pub remote_ext_config: Option<String>,
#[arg(long, default_value_t = 3080)]
pub http_port: u16,
#[arg(short = 'D', long, value_name = "DATADIR")]
pub pgdata: String,
#[arg(short = 'C', long, value_name = "DATABASE_URL")]
pub connstr: String,
#[cfg(target_os = "linux")]
#[arg(long, default_value = "neon-postgres")]
pub cgroup: String,
#[cfg(target_os = "linux")]
#[arg(
long,
default_value = "host=localhost port=5432 dbname=postgres user=cloud_admin sslmode=disable application_name=vm-monitor"
)]
pub filecache_connstr: String,
#[cfg(target_os = "linux")]
#[arg(long, default_value = "0.0.0.0:10301")]
pub vm_monitor_addr: String,
#[arg(long, action = clap::ArgAction::SetTrue)]
pub resize_swap_on_bind: bool,
#[arg(long)]
pub set_disk_quota_for_fs: Option<String>,
#[arg(short = 's', long = "spec", group = "spec")]
pub spec_json: Option<String>,
#[arg(short = 'S', long, group = "spec-path")]
pub spec_path: Option<OsString>,
#[arg(short = 'i', long, group = "compute-id", conflicts_with_all = ["spec", "spec-path"])]
pub compute_id: Option<String>,
#[arg(short = 'p', long, conflicts_with_all = ["spec", "spec-path"], requires = "compute-id", value_name = "CONTROL_PLANE_API_BASE_URL")]
pub control_plane_uri: Option<String>,
}
fn main() -> Result<()> {
let cli = Cli::parse();
let build_tag = init()?;
let scenario = failpoint_support::init();
let (build_tag, clap_args) = init()?;
// enable core dumping for all child processes
setrlimit(Resource::CORE, rlimit::INFINITY, rlimit::INFINITY)?;
@@ -151,11 +81,13 @@ fn main() -> Result<()> {
// Enter startup tracing context
let _startup_context_guard = startup_context_from_env();
let cli_spec = try_spec_from_cli(&cli)?;
let cli_args = process_cli(&clap_args)?;
let compute = wait_spec(build_tag, &cli, cli_spec)?;
let cli_spec = try_spec_from_cli(&clap_args, &cli_args)?;
start_postgres(&cli, compute)?
let wait_spec_result = wait_spec(build_tag, cli_args, cli_spec)?;
start_postgres(&clap_args, wait_spec_result)?
// Startup is finished, exit the startup tracing span
};
@@ -167,12 +99,10 @@ fn main() -> Result<()> {
maybe_delay_exit(delay_exit);
scenario.teardown();
deinit_and_exit(wait_pg_result);
}
fn init() -> Result<String> {
fn init() -> Result<(String, clap::ArgMatches)> {
init_tracing_and_logging(DEFAULT_LOG_LEVEL)?;
let mut signals = Signals::new([SIGINT, SIGTERM, SIGQUIT])?;
@@ -187,7 +117,66 @@ fn init() -> Result<String> {
.to_string();
info!("build_tag: {build_tag}");
Ok(build_tag)
Ok((build_tag, cli().get_matches()))
}
fn process_cli(matches: &clap::ArgMatches) -> Result<ProcessCliResult> {
let pgbin_default = "postgres";
let pgbin = matches
.get_one::<String>("pgbin")
.map(|s| s.as_str())
.unwrap_or(pgbin_default);
let ext_remote_storage = matches
.get_one::<String>("remote-ext-config")
// Compatibility hack: if the control plane specified any remote-ext-config
// use the default value for extension storage proxy gateway.
// Remove this once the control plane is updated to pass the gateway URL
.map(|conf| {
if conf.starts_with("http") {
conf.trim_end_matches('/')
} else {
"http://pg-ext-s3-gateway"
}
});
let http_port = *matches
.get_one::<u16>("http-port")
.expect("http-port is required");
let pgdata = matches
.get_one::<String>("pgdata")
.expect("PGDATA path is required");
let connstr = matches
.get_one::<String>("connstr")
.expect("Postgres connection string is required");
let spec_json = matches.get_one::<String>("spec");
let spec_path = matches.get_one::<String>("spec-path");
let resize_swap_on_bind = matches.get_flag("resize-swap-on-bind");
let set_disk_quota_for_fs = matches.get_one::<String>("set-disk-quota-for-fs");
Ok(ProcessCliResult {
connstr,
pgdata,
pgbin,
ext_remote_storage,
http_port,
spec_json,
spec_path,
resize_swap_on_bind,
set_disk_quota_for_fs,
})
}
struct ProcessCliResult<'clap> {
connstr: &'clap str,
pgdata: &'clap str,
pgbin: &'clap str,
ext_remote_storage: Option<&'clap str>,
http_port: u16,
spec_json: Option<&'clap String>,
spec_path: Option<&'clap String>,
resize_swap_on_bind: bool,
set_disk_quota_for_fs: Option<&'clap String>,
}
fn startup_context_from_env() -> Option<opentelemetry::ContextGuard> {
@@ -240,52 +229,58 @@ fn startup_context_from_env() -> Option<opentelemetry::ContextGuard> {
}
}
fn try_spec_from_cli(cli: &Cli) -> Result<CliSpecParams> {
// First, try to get cluster spec from the cli argument
if let Some(ref spec_json) = cli.spec_json {
info!("got spec from cli argument {}", spec_json);
return Ok(CliSpecParams {
spec: Some(serde_json::from_str(spec_json)?),
live_config_allowed: false,
});
}
fn try_spec_from_cli(
matches: &clap::ArgMatches,
ProcessCliResult {
spec_json,
spec_path,
..
}: &ProcessCliResult,
) -> Result<CliSpecParams> {
let compute_id = matches.get_one::<String>("compute-id");
let control_plane_uri = matches.get_one::<String>("control-plane-uri");
// Second, try to read it from the file if path is provided
if let Some(ref spec_path) = cli.spec_path {
let file = File::open(Path::new(spec_path))?;
return Ok(CliSpecParams {
spec: Some(serde_json::from_reader(file)?),
live_config_allowed: true,
});
}
if cli.compute_id.is_none() {
panic!(
"compute spec should be provided by one of the following ways: \
--spec OR --spec-path OR --control-plane-uri and --compute-id"
);
};
if cli.control_plane_uri.is_none() {
panic!("must specify both --control-plane-uri and --compute-id or none");
};
match get_spec_from_control_plane(
cli.control_plane_uri.as_ref().unwrap(),
cli.compute_id.as_ref().unwrap(),
) {
Ok(spec) => Ok(CliSpecParams {
spec,
live_config_allowed: true,
}),
Err(e) => {
error!(
"cannot get response from control plane: {}\n\
neither spec nor confirmation that compute is in the Empty state was received",
e
);
Err(e)
let spec;
let mut live_config_allowed = false;
match spec_json {
// First, try to get cluster spec from the cli argument
Some(json) => {
info!("got spec from cli argument {}", json);
spec = Some(serde_json::from_str(json)?);
}
}
None => {
// Second, try to read it from the file if path is provided
if let Some(sp) = spec_path {
let path = Path::new(sp);
let file = File::open(path)?;
spec = Some(serde_json::from_reader(file)?);
live_config_allowed = true;
} else if let Some(id) = compute_id {
if let Some(cp_base) = control_plane_uri {
live_config_allowed = true;
spec = match get_spec_from_control_plane(cp_base, id) {
Ok(s) => s,
Err(e) => {
error!("cannot get response from control plane: {}", e);
panic!("neither spec nor confirmation that compute is in the Empty state was received");
}
};
} else {
panic!("must specify both --control-plane-uri and --compute-id or none");
}
} else {
panic!(
"compute spec should be provided by one of the following ways: \
--spec OR --spec-path OR --control-plane-uri and --compute-id"
);
}
}
};
Ok(CliSpecParams {
spec,
live_config_allowed,
})
}
struct CliSpecParams {
@@ -296,12 +291,21 @@ struct CliSpecParams {
fn wait_spec(
build_tag: String,
cli: &Cli,
ProcessCliResult {
connstr,
pgdata,
pgbin,
ext_remote_storage,
resize_swap_on_bind,
set_disk_quota_for_fs,
http_port,
..
}: ProcessCliResult,
CliSpecParams {
spec,
live_config_allowed,
}: CliSpecParams,
) -> Result<Arc<ComputeNode>> {
) -> Result<WaitSpecResult> {
let mut new_state = ComputeState::new();
let spec_set;
@@ -313,23 +317,15 @@ fn wait_spec(
} else {
spec_set = false;
}
let connstr = Url::parse(&cli.connstr).context("cannot parse connstr as a URL")?;
let conn_conf = postgres::config::Config::from_str(connstr.as_str())
.context("cannot build postgres config from connstr")?;
let tokio_conn_conf = tokio_postgres::config::Config::from_str(connstr.as_str())
.context("cannot build tokio postgres config from connstr")?;
let compute_node = ComputeNode {
connstr,
conn_conf,
tokio_conn_conf,
pgdata: cli.pgdata.clone(),
pgbin: cli.pgbin.clone(),
pgversion: get_pg_version_string(&cli.pgbin),
http_port: cli.http_port,
connstr: Url::parse(connstr).context("cannot parse connstr as a URL")?,
pgdata: pgdata.to_string(),
pgbin: pgbin.to_string(),
pgversion: get_pg_version(pgbin),
live_config_allowed,
state: Mutex::new(new_state),
state_changed: Condvar::new(),
ext_remote_storage: cli.remote_ext_config.clone(),
ext_remote_storage: ext_remote_storage.map(|s| s.to_string()),
ext_download_progress: RwLock::new(HashMap::new()),
build_tag,
};
@@ -346,7 +342,7 @@ fn wait_spec(
// Launch http service first, so that we can serve control-plane requests
// while configuration is still in progress.
let _http_handle =
launch_http_server(cli.http_port, &compute).expect("cannot launch http endpoint thread");
launch_http_server(http_port, &compute).expect("cannot launch http endpoint thread");
if !spec_set {
// No spec provided, hang waiting for it.
@@ -378,12 +374,31 @@ fn wait_spec(
launch_lsn_lease_bg_task_for_static(&compute);
Ok(compute)
Ok(WaitSpecResult {
compute,
http_port,
resize_swap_on_bind,
set_disk_quota_for_fs: set_disk_quota_for_fs.cloned(),
})
}
struct WaitSpecResult {
compute: Arc<ComputeNode>,
// passed through from ProcessCliResult
http_port: u16,
resize_swap_on_bind: bool,
set_disk_quota_for_fs: Option<String>,
}
fn start_postgres(
cli: &Cli,
compute: Arc<ComputeNode>,
// need to allow unused because `matches` is only used if target_os = "linux"
#[allow(unused_variables)] matches: &clap::ArgMatches,
WaitSpecResult {
compute,
http_port,
resize_swap_on_bind,
set_disk_quota_for_fs,
}: WaitSpecResult,
) -> Result<(Option<PostgresHandle>, StartPostgresResult)> {
// We got all we need, update the state.
let mut state = compute.state.lock().unwrap();
@@ -393,14 +408,9 @@ fn start_postgres(
"running compute with features: {:?}",
state.pspec.as_ref().unwrap().spec.features
);
// before we release the mutex, fetch some parameters for later.
let &ComputeSpec {
swap_size_bytes,
disk_quota_bytes,
#[cfg(target_os = "linux")]
disable_lfc_resizing,
..
} = &state.pspec.as_ref().unwrap().spec;
// before we release the mutex, fetch the swap size (if any) for later.
let swap_size_bytes = state.pspec.as_ref().unwrap().spec.swap_size_bytes;
let disk_quota_bytes = state.pspec.as_ref().unwrap().spec.disk_quota_bytes;
drop(state);
// Launch remaining service threads
@@ -411,7 +421,7 @@ fn start_postgres(
let mut delay_exit = false;
// Resize swap to the desired size if the compute spec says so
if let (Some(size_bytes), true) = (swap_size_bytes, cli.resize_swap_on_bind) {
if let (Some(size_bytes), true) = (swap_size_bytes, resize_swap_on_bind) {
// To avoid 'swapoff' hitting postgres startup, we need to run resize-swap to completion
// *before* starting postgres.
//
@@ -438,9 +448,9 @@ fn start_postgres(
// Set disk quota if the compute spec says so
if let (Some(disk_quota_bytes), Some(disk_quota_fs_mountpoint)) =
(disk_quota_bytes, cli.set_disk_quota_for_fs.as_ref())
(disk_quota_bytes, set_disk_quota_for_fs)
{
match set_disk_quota(disk_quota_bytes, disk_quota_fs_mountpoint) {
match set_disk_quota(disk_quota_bytes, &disk_quota_fs_mountpoint) {
Ok(()) => {
let size_mib = disk_quota_bytes as f32 / (1 << 20) as f32; // just for more coherent display.
info!(%disk_quota_bytes, %size_mib, "set disk quota");
@@ -458,14 +468,13 @@ fn start_postgres(
}
}
let extension_server_port: u16 = http_port;
// Start Postgres
let mut pg = None;
if !prestartup_failed {
pg = match compute.start_compute() {
Ok(pg) => {
info!(postmaster_pid = %pg.0.id(), "Postgres was started");
Some(pg)
}
pg = match compute.start_compute(extension_server_port) {
Ok(pg) => Some(pg),
Err(err) => {
error!("could not start the compute node: {:#}", err);
compute.set_failed_status(err);
@@ -483,7 +492,13 @@ fn start_postgres(
if #[cfg(target_os = "linux")] {
use std::env;
use tokio_util::sync::CancellationToken;
let vm_monitor_addr = matches
.get_one::<String>("vm-monitor-addr")
.expect("--vm-monitor-addr should always be set because it has a default arg");
let file_cache_connstr = matches.get_one::<String>("filecache-connstr");
let cgroup = matches.get_one::<String>("cgroup");
// Only make a runtime if we need to.
// Note: it seems like you can make a runtime in an inner scope and
// if you start a task in it it won't be dropped. However, make it
// in the outermost scope just to be safe.
@@ -502,19 +517,12 @@ fn start_postgres(
// This token is used internally by the monitor to clean up all threads
let token = CancellationToken::new();
// don't pass postgres connection string to vm-monitor if we don't want it to resize LFC
let pgconnstr = if disable_lfc_resizing.unwrap_or(false) {
None
} else {
Some(cli.filecache_connstr.clone())
};
let vm_monitor = rt.as_ref().map(|rt| {
rt.spawn(vm_monitor::start(
Box::leak(Box::new(vm_monitor::Args {
cgroup: Some(cli.cgroup.clone()),
pgconnstr,
addr: cli.vm_monitor_addr.clone(),
cgroup: cgroup.cloned(),
pgconnstr: file_cache_connstr.cloned(),
addr: vm_monitor_addr.clone(),
})),
token.clone(),
))
@@ -557,8 +565,6 @@ fn wait_postgres(pg: Option<PostgresHandle>) -> Result<WaitPostgresResult> {
// propagate to Postgres and it will be shut down as well.
let mut exit_code = None;
if let Some((mut pg, logs_handle)) = pg {
info!(postmaster_pid = %pg.id(), "Waiting for Postgres to exit");
let ecode = pg
.wait()
.expect("failed to start waiting on Postgres process");
@@ -670,6 +676,105 @@ fn deinit_and_exit(WaitPostgresResult { exit_code }: WaitPostgresResult) -> ! {
exit(exit_code.unwrap_or(1))
}
fn cli() -> clap::Command {
// Env variable is set by `cargo`
let version = option_env!("CARGO_PKG_VERSION").unwrap_or("unknown");
clap::Command::new("compute_ctl")
.version(version)
.arg(
Arg::new("http-port")
.long("http-port")
.value_name("HTTP_PORT")
.default_value("3080")
.value_parser(clap::value_parser!(u16))
.required(false),
)
.arg(
Arg::new("connstr")
.short('C')
.long("connstr")
.value_name("DATABASE_URL")
.required(true),
)
.arg(
Arg::new("pgdata")
.short('D')
.long("pgdata")
.value_name("DATADIR")
.required(true),
)
.arg(
Arg::new("pgbin")
.short('b')
.long("pgbin")
.default_value("postgres")
.value_name("POSTGRES_PATH"),
)
.arg(
Arg::new("spec")
.short('s')
.long("spec")
.value_name("SPEC_JSON"),
)
.arg(
Arg::new("spec-path")
.short('S')
.long("spec-path")
.value_name("SPEC_PATH"),
)
.arg(
Arg::new("compute-id")
.short('i')
.long("compute-id")
.value_name("COMPUTE_ID"),
)
.arg(
Arg::new("control-plane-uri")
.short('p')
.long("control-plane-uri")
.value_name("CONTROL_PLANE_API_BASE_URI"),
)
.arg(
Arg::new("remote-ext-config")
.short('r')
.long("remote-ext-config")
.value_name("REMOTE_EXT_CONFIG"),
)
// TODO(fprasx): we currently have default arguments because the cloud PR
// to pass them in hasn't been merged yet. We should get rid of them once
// the PR is merged.
.arg(
Arg::new("vm-monitor-addr")
.long("vm-monitor-addr")
.default_value("0.0.0.0:10301")
.value_name("VM_MONITOR_ADDR"),
)
.arg(
Arg::new("cgroup")
.long("cgroup")
.default_value("neon-postgres")
.value_name("CGROUP"),
)
.arg(
Arg::new("filecache-connstr")
.long("filecache-connstr")
.default_value(
"host=localhost port=5432 dbname=postgres user=cloud_admin sslmode=disable application_name=vm-monitor",
)
.value_name("FILECACHE_CONNSTR"),
)
.arg(
Arg::new("resize-swap-on-bind")
.long("resize-swap-on-bind")
.action(clap::ArgAction::SetTrue),
)
.arg(
Arg::new("set-disk-quota-for-fs")
.long("set-disk-quota-for-fs")
.value_name("SET_DISK_QUOTA_FOR_FS")
)
}
/// 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.
@@ -679,14 +784,7 @@ fn handle_exit_signal(sig: i32) {
exit(1);
}
#[cfg(test)]
mod test {
use clap::CommandFactory;
use super::Cli;
#[test]
fn verify_cli() {
Cli::command().debug_assert()
}
#[test]
fn verify_cli() {
cli().debug_assert()
}

View File

@@ -1,438 +0,0 @@
//! This program dumps a remote Postgres database into a local Postgres database
//! and uploads the resulting PGDATA into object storage for import into a Timeline.
//!
//! # Context, Architecture, Design
//!
//! See cloud.git Fast Imports RFC (<https://github.com/neondatabase/cloud/pull/19799>)
//! for the full picture.
//! The RFC describing the storage pieces of importing the PGDATA dump into a Timeline
//! is publicly accessible at <https://github.com/neondatabase/neon/pull/9538>.
//!
//! # This is a Prototype!
//!
//! This program is part of a prototype feature and not yet used in production.
//!
//! The cloud.git RFC contains lots of suggestions for improving e2e throughput
//! of this step of the timeline import process.
//!
//! # Local Testing
//!
//! - Comment out most of the pgxns in compute-node.Dockerfile to speed up the build.
//! - Build the image with the following command:
//!
//! ```bash
//! docker buildx build --platform linux/amd64 --build-arg DEBIAN_VERSION=bullseye --build-arg GIT_VERSION=local --build-arg PG_VERSION=v14 --build-arg BUILD_TAG="$(date --iso-8601=s -u)" -t localhost:3030/localregistry/compute-node-v14:latest -f compute/compute-node.Dockerfile .
//! docker push localhost:3030/localregistry/compute-node-v14:latest
//! ```
use anyhow::Context;
use aws_config::BehaviorVersion;
use camino::{Utf8Path, Utf8PathBuf};
use clap::Parser;
use compute_tools::extension_server::{get_pg_version, PostgresMajorVersion};
use nix::unistd::Pid;
use tracing::{error, info, info_span, warn, Instrument};
use utils::fs_ext::is_directory_empty;
#[path = "fast_import/aws_s3_sync.rs"]
mod aws_s3_sync;
#[path = "fast_import/child_stdio_to_log.rs"]
mod child_stdio_to_log;
#[path = "fast_import/s3_uri.rs"]
mod s3_uri;
const PG_WAIT_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(600);
const PG_WAIT_RETRY_INTERVAL: std::time::Duration = std::time::Duration::from_millis(300);
#[derive(clap::Parser)]
struct Args {
#[clap(long)]
working_directory: Utf8PathBuf,
#[clap(long, env = "NEON_IMPORTER_S3_PREFIX")]
s3_prefix: Option<s3_uri::S3Uri>,
#[clap(long)]
source_connection_string: Option<String>,
#[clap(short, long)]
interactive: bool,
#[clap(long)]
pg_bin_dir: Utf8PathBuf,
#[clap(long)]
pg_lib_dir: Utf8PathBuf,
#[clap(long)]
pg_port: Option<u16>, // port to run postgres on, 5432 is default
}
#[serde_with::serde_as]
#[derive(serde::Deserialize)]
struct Spec {
encryption_secret: EncryptionSecret,
#[serde_as(as = "serde_with::base64::Base64")]
source_connstring_ciphertext_base64: Vec<u8>,
}
#[derive(serde::Deserialize)]
enum EncryptionSecret {
#[allow(clippy::upper_case_acronyms)]
KMS { key_id: String },
}
// copied from pageserver_api::config::defaults::DEFAULT_LOCALE to avoid dependency just for a constant
const DEFAULT_LOCALE: &str = if cfg!(target_os = "macos") {
"C"
} else {
"C.UTF-8"
};
#[tokio::main]
pub(crate) async fn main() -> anyhow::Result<()> {
utils::logging::init(
utils::logging::LogFormat::Plain,
utils::logging::TracingErrorLayerEnablement::EnableWithRustLogFilter,
utils::logging::Output::Stdout,
)?;
info!("starting");
let args = Args::parse();
// Validate arguments
if args.s3_prefix.is_none() && args.source_connection_string.is_none() {
anyhow::bail!("either s3_prefix or source_connection_string must be specified");
}
if args.s3_prefix.is_some() && args.source_connection_string.is_some() {
anyhow::bail!("only one of s3_prefix or source_connection_string can be specified");
}
let working_directory = args.working_directory;
let pg_bin_dir = args.pg_bin_dir;
let pg_lib_dir = args.pg_lib_dir;
let pg_port = args.pg_port.unwrap_or_else(|| {
info!("pg_port not specified, using default 5432");
5432
});
// Initialize AWS clients only if s3_prefix is specified
let (aws_config, kms_client) = if args.s3_prefix.is_some() {
let config = aws_config::load_defaults(BehaviorVersion::v2024_03_28()).await;
let kms = aws_sdk_kms::Client::new(&config);
(Some(config), Some(kms))
} else {
(None, None)
};
// Get source connection string either from S3 spec or direct argument
let source_connection_string = if let Some(s3_prefix) = &args.s3_prefix {
let spec: Spec = {
let spec_key = s3_prefix.append("/spec.json");
let s3_client = aws_sdk_s3::Client::new(aws_config.as_ref().unwrap());
let object = s3_client
.get_object()
.bucket(&spec_key.bucket)
.key(spec_key.key)
.send()
.await
.context("get spec from s3")?
.body
.collect()
.await
.context("download spec body")?;
serde_json::from_slice(&object.into_bytes()).context("parse spec as json")?
};
match spec.encryption_secret {
EncryptionSecret::KMS { key_id } => {
let mut output = kms_client
.unwrap()
.decrypt()
.key_id(key_id)
.ciphertext_blob(aws_sdk_s3::primitives::Blob::new(
spec.source_connstring_ciphertext_base64,
))
.send()
.await
.context("decrypt source connection string")?;
let plaintext = output
.plaintext
.take()
.context("get plaintext source connection string")?;
String::from_utf8(plaintext.into_inner())
.context("parse source connection string as utf8")?
}
}
} else {
args.source_connection_string.unwrap()
};
match tokio::fs::create_dir(&working_directory).await {
Ok(()) => {}
Err(e) if e.kind() == std::io::ErrorKind::AlreadyExists => {
if !is_directory_empty(&working_directory)
.await
.context("check if working directory is empty")?
{
anyhow::bail!("working directory is not empty");
} else {
// ok
}
}
Err(e) => return Err(anyhow::Error::new(e).context("create working directory")),
}
let pgdata_dir = working_directory.join("pgdata");
tokio::fs::create_dir(&pgdata_dir)
.await
.context("create pgdata directory")?;
let pgbin = pg_bin_dir.join("postgres");
let pg_version = match get_pg_version(pgbin.as_ref()) {
PostgresMajorVersion::V14 => 14,
PostgresMajorVersion::V15 => 15,
PostgresMajorVersion::V16 => 16,
PostgresMajorVersion::V17 => 17,
};
let superuser = "cloud_admin"; // XXX: this shouldn't be hard-coded
postgres_initdb::do_run_initdb(postgres_initdb::RunInitdbArgs {
superuser,
locale: DEFAULT_LOCALE, // XXX: this shouldn't be hard-coded,
pg_version,
initdb_bin: pg_bin_dir.join("initdb").as_ref(),
library_search_path: &pg_lib_dir, // TODO: is this right? Prob works in compute image, not sure about neon_local.
pgdata: &pgdata_dir,
})
.await
.context("initdb")?;
let nproc = num_cpus::get();
//
// Launch postgres process
//
let mut postgres_proc = tokio::process::Command::new(pgbin)
.arg("-D")
.arg(&pgdata_dir)
.args(["-p", &format!("{pg_port}")])
.args(["-c", "wal_level=minimal"])
.args(["-c", "shared_buffers=10GB"])
.args(["-c", "max_wal_senders=0"])
.args(["-c", "fsync=off"])
.args(["-c", "full_page_writes=off"])
.args(["-c", "synchronous_commit=off"])
.args(["-c", "maintenance_work_mem=8388608"])
.args(["-c", &format!("max_parallel_maintenance_workers={nproc}")])
.args(["-c", &format!("max_parallel_workers={nproc}")])
.args(["-c", &format!("max_parallel_workers_per_gather={nproc}")])
.args(["-c", &format!("max_worker_processes={nproc}")])
.args([
"-c",
&format!(
"effective_io_concurrency={}",
if cfg!(target_os = "macos") { 0 } else { 100 }
),
])
.env_clear()
.env("LD_LIBRARY_PATH", &pg_lib_dir)
.env(
"ASAN_OPTIONS",
std::env::var("ASAN_OPTIONS").unwrap_or_default(),
)
.env(
"UBSAN_OPTIONS",
std::env::var("UBSAN_OPTIONS").unwrap_or_default(),
)
.stdout(std::process::Stdio::piped())
.stderr(std::process::Stdio::piped())
.spawn()
.context("spawn postgres")?;
info!("spawned postgres, waiting for it to become ready");
tokio::spawn(
child_stdio_to_log::relay_process_output(
postgres_proc.stdout.take(),
postgres_proc.stderr.take(),
)
.instrument(info_span!("postgres")),
);
// Create neondb database in the running postgres
let restore_pg_connstring =
format!("host=localhost port={pg_port} user={superuser} dbname=postgres");
let start_time = std::time::Instant::now();
loop {
if start_time.elapsed() > PG_WAIT_TIMEOUT {
error!(
"timeout exceeded: failed to poll postgres and create database within 10 minutes"
);
std::process::exit(1);
}
match tokio_postgres::connect(&restore_pg_connstring, tokio_postgres::NoTls).await {
Ok((client, connection)) => {
// Spawn the connection handling task to maintain the connection
tokio::spawn(async move {
if let Err(e) = connection.await {
warn!("connection error: {}", e);
}
});
match client.simple_query("CREATE DATABASE neondb;").await {
Ok(_) => {
info!("created neondb database");
break;
}
Err(e) => {
warn!(
"failed to create database: {}, retying in {}s",
e,
PG_WAIT_RETRY_INTERVAL.as_secs_f32()
);
tokio::time::sleep(PG_WAIT_RETRY_INTERVAL).await;
continue;
}
}
}
Err(_) => {
info!(
"postgres not ready yet, retrying in {}s",
PG_WAIT_RETRY_INTERVAL.as_secs_f32()
);
tokio::time::sleep(PG_WAIT_RETRY_INTERVAL).await;
continue;
}
}
}
let restore_pg_connstring = restore_pg_connstring.replace("dbname=postgres", "dbname=neondb");
let dumpdir = working_directory.join("dumpdir");
let common_args = [
// schema mapping (prob suffices to specify them on one side)
"--no-owner".to_string(),
"--no-privileges".to_string(),
"--no-publications".to_string(),
"--no-security-labels".to_string(),
"--no-subscriptions".to_string(),
"--no-tablespaces".to_string(),
// format
"--format".to_string(),
"directory".to_string(),
// concurrency
"--jobs".to_string(),
num_cpus::get().to_string(),
// progress updates
"--verbose".to_string(),
];
info!("dump into the working directory");
{
let mut pg_dump = tokio::process::Command::new(pg_bin_dir.join("pg_dump"))
.args(&common_args)
.arg("-f")
.arg(&dumpdir)
.arg("--no-sync")
// POSITIONAL args
// source db (db name included in connection string)
.arg(&source_connection_string)
// how we run it
.env_clear()
.env("LD_LIBRARY_PATH", &pg_lib_dir)
.kill_on_drop(true)
.stdout(std::process::Stdio::piped())
.stderr(std::process::Stdio::piped())
.spawn()
.context("spawn pg_dump")?;
info!(pid=%pg_dump.id().unwrap(), "spawned pg_dump");
tokio::spawn(
child_stdio_to_log::relay_process_output(pg_dump.stdout.take(), pg_dump.stderr.take())
.instrument(info_span!("pg_dump")),
);
let st = pg_dump.wait().await.context("wait for pg_dump")?;
info!(status=?st, "pg_dump exited");
if !st.success() {
warn!(status=%st, "pg_dump failed, restore will likely fail as well");
}
}
// TODO: do it in a streaming way, plenty of internal research done on this already
// TODO: do the unlogged table trick
info!("restore from working directory into vanilla postgres");
{
let mut pg_restore = tokio::process::Command::new(pg_bin_dir.join("pg_restore"))
.args(&common_args)
.arg("-d")
.arg(&restore_pg_connstring)
// POSITIONAL args
.arg(&dumpdir)
// how we run it
.env_clear()
.env("LD_LIBRARY_PATH", &pg_lib_dir)
.kill_on_drop(true)
.stdout(std::process::Stdio::piped())
.stderr(std::process::Stdio::piped())
.spawn()
.context("spawn pg_restore")?;
info!(pid=%pg_restore.id().unwrap(), "spawned pg_restore");
tokio::spawn(
child_stdio_to_log::relay_process_output(
pg_restore.stdout.take(),
pg_restore.stderr.take(),
)
.instrument(info_span!("pg_restore")),
);
let st = pg_restore.wait().await.context("wait for pg_restore")?;
info!(status=?st, "pg_restore exited");
if !st.success() {
warn!(status=%st, "pg_restore failed, restore will likely fail as well");
}
}
// If interactive mode, wait for Ctrl+C
if args.interactive {
info!("Running in interactive mode. Press Ctrl+C to shut down.");
tokio::signal::ctrl_c().await.context("wait for ctrl-c")?;
}
info!("shutdown postgres");
{
nix::sys::signal::kill(
Pid::from_raw(
i32::try_from(postgres_proc.id().unwrap()).expect("convert child pid to i32"),
),
nix::sys::signal::SIGTERM,
)
.context("signal postgres to shut down")?;
postgres_proc
.wait()
.await
.context("wait for postgres to shut down")?;
}
// Only sync if s3_prefix was specified
if let Some(s3_prefix) = args.s3_prefix {
info!("upload pgdata");
aws_s3_sync::sync(Utf8Path::new(&pgdata_dir), &s3_prefix.append("/pgdata/"))
.await
.context("sync dump directory to destination")?;
info!("write status");
{
let status_dir = working_directory.join("status");
std::fs::create_dir(&status_dir).context("create status directory")?;
let status_file = status_dir.join("pgdata");
std::fs::write(&status_file, serde_json::json!({"done": true}).to_string())
.context("write status file")?;
aws_s3_sync::sync(&status_dir, &s3_prefix.append("/status/"))
.await
.context("sync status directory to destination")?;
}
}
Ok(())
}

View File

@@ -1,24 +0,0 @@
use anyhow::Context;
use camino::Utf8Path;
use super::s3_uri::S3Uri;
pub(crate) async fn sync(local: &Utf8Path, remote: &S3Uri) -> anyhow::Result<()> {
let mut builder = tokio::process::Command::new("aws");
builder
.arg("s3")
.arg("sync")
.arg(local.as_str())
.arg(remote.to_string());
let st = builder
.spawn()
.context("spawn aws s3 sync")?
.wait()
.await
.context("wait for aws s3 sync")?;
if st.success() {
Ok(())
} else {
Err(anyhow::anyhow!("aws s3 sync failed"))
}
}

View File

@@ -1,35 +0,0 @@
use tokio::io::{AsyncBufReadExt, BufReader};
use tokio::process::{ChildStderr, ChildStdout};
use tracing::info;
/// Asynchronously relays the output from a child process's `stdout` and `stderr` to the tracing log.
/// Each line is read and logged individually, with lossy UTF-8 conversion.
///
/// # Arguments
///
/// * `stdout`: An `Option<ChildStdout>` from the child process.
/// * `stderr`: An `Option<ChildStderr>` from the child process.
///
pub(crate) async fn relay_process_output(stdout: Option<ChildStdout>, stderr: Option<ChildStderr>) {
let stdout_fut = async {
if let Some(stdout) = stdout {
let reader = BufReader::new(stdout);
let mut lines = reader.lines();
while let Ok(Some(line)) = lines.next_line().await {
info!(fd = "stdout", "{}", line);
}
}
};
let stderr_fut = async {
if let Some(stderr) = stderr {
let reader = BufReader::new(stderr);
let mut lines = reader.lines();
while let Ok(Some(line)) = lines.next_line().await {
info!(fd = "stderr", "{}", line);
}
}
};
tokio::join!(stdout_fut, stderr_fut);
}

View File

@@ -1,75 +0,0 @@
use anyhow::Result;
use std::str::FromStr;
/// Struct to hold parsed S3 components
#[derive(Debug, Clone, PartialEq, Eq)]
pub struct S3Uri {
pub bucket: String,
pub key: String,
}
impl FromStr for S3Uri {
type Err = anyhow::Error;
/// Parse an S3 URI into a bucket and key
fn from_str(uri: &str) -> Result<Self> {
// Ensure the URI starts with "s3://"
if !uri.starts_with("s3://") {
return Err(anyhow::anyhow!("Invalid S3 URI scheme"));
}
// Remove the "s3://" prefix
let stripped_uri = &uri[5..];
// Split the remaining string into bucket and key parts
if let Some((bucket, key)) = stripped_uri.split_once('/') {
Ok(S3Uri {
bucket: bucket.to_string(),
key: key.to_string(),
})
} else {
Err(anyhow::anyhow!(
"Invalid S3 URI format, missing bucket or key"
))
}
}
}
impl S3Uri {
pub fn append(&self, suffix: &str) -> Self {
Self {
bucket: self.bucket.clone(),
key: format!("{}{}", self.key, suffix),
}
}
}
impl std::fmt::Display for S3Uri {
fn fmt(&self, f: &mut std::fmt::Formatter) -> std::fmt::Result {
write!(f, "s3://{}/{}", self.bucket, self.key)
}
}
impl clap::builder::TypedValueParser for S3Uri {
type Value = Self;
fn parse_ref(
&self,
_cmd: &clap::Command,
_arg: Option<&clap::Arg>,
value: &std::ffi::OsStr,
) -> Result<Self::Value, clap::Error> {
let value_str = value.to_str().ok_or_else(|| {
clap::Error::raw(
clap::error::ErrorKind::InvalidUtf8,
"Invalid UTF-8 sequence",
)
})?;
S3Uri::from_str(value_str).map_err(|e| {
clap::Error::raw(
clap::error::ErrorKind::InvalidValue,
format!("Failed to parse S3 URI: {}", e),
)
})
}
}

View File

@@ -1,47 +1,46 @@
use compute_api::{
responses::CatalogObjects,
spec::{Database, Role},
};
use futures::Stream;
use postgres::NoTls;
use postgres::{Client, NoTls};
use std::{path::Path, process::Stdio, result::Result, sync::Arc};
use tokio::{
io::{AsyncBufReadExt, BufReader},
process::Command,
spawn,
task,
};
use tokio_stream::{self as stream, StreamExt};
use tokio_util::codec::{BytesCodec, FramedRead};
use tracing::warn;
use crate::compute::ComputeNode;
use crate::pg_helpers::{get_existing_dbs_async, get_existing_roles_async, postgres_conf_for_db};
use compute_api::responses::CatalogObjects;
use crate::{
compute::ComputeNode,
pg_helpers::{get_existing_dbs, get_existing_roles},
};
pub async fn get_dbs_and_roles(compute: &Arc<ComputeNode>) -> anyhow::Result<CatalogObjects> {
let conf = compute.get_tokio_conn_conf(Some("compute_ctl:get_dbs_and_roles"));
let (client, connection): (tokio_postgres::Client, _) = conf.connect(NoTls).await?;
spawn(async move {
if let Err(e) = connection.await {
eprintln!("connection error: {}", e);
let connstr = compute.connstr.clone();
task::spawn_blocking(move || {
let mut client = Client::connect(connstr.as_str(), NoTls)?;
let roles: Vec<Role>;
{
let mut xact = client.transaction()?;
roles = get_existing_roles(&mut xact)?;
}
});
let databases: Vec<Database> = get_existing_dbs(&mut client)?.values().cloned().collect();
let roles = get_existing_roles_async(&client).await?;
let databases = get_existing_dbs_async(&client)
.await?
.into_values()
.collect();
Ok(CatalogObjects { roles, databases })
Ok(CatalogObjects { roles, databases })
})
.await?
}
#[derive(Debug, thiserror::Error)]
pub enum SchemaDumpError {
#[error("database does not exist")]
#[error("Database does not exist.")]
DatabaseDoesNotExist,
#[error("failed to execute pg_dump")]
#[error("Failed to execute pg_dump.")]
IO(#[from] std::io::Error),
#[error("unexpected I/O error")]
Unexpected,
}
// It uses the pg_dump utility to dump the schema of the specified database.
@@ -59,38 +58,11 @@ pub async fn get_database_schema(
let pgbin = &compute.pgbin;
let basepath = Path::new(pgbin).parent().unwrap();
let pgdump = basepath.join("pg_dump");
// Replace the DB in the connection string and disable it to parts.
// This is the only option to handle DBs with special characters.
let conf =
postgres_conf_for_db(&compute.connstr, dbname).map_err(|_| SchemaDumpError::Unexpected)?;
let host = conf
.get_hosts()
.first()
.ok_or(SchemaDumpError::Unexpected)?;
let host = match host {
tokio_postgres::config::Host::Tcp(ip) => ip.to_string(),
#[cfg(unix)]
tokio_postgres::config::Host::Unix(path) => path.to_string_lossy().to_string(),
};
let port = conf
.get_ports()
.first()
.ok_or(SchemaDumpError::Unexpected)?;
let user = conf.get_user().ok_or(SchemaDumpError::Unexpected)?;
let dbname = conf.get_dbname().ok_or(SchemaDumpError::Unexpected)?;
let mut connstr = compute.connstr.clone();
connstr.set_path(dbname);
let mut cmd = Command::new(pgdump)
// XXX: this seems to be the only option to deal with DBs with `=` in the name
// See <https://www.postgresql.org/message-id/flat/20151023003445.931.91267%40wrigleys.postgresql.org>
.env("PGDATABASE", dbname)
.arg("--host")
.arg(host)
.arg("--port")
.arg(port.to_string())
.arg("--username")
.arg(user)
.arg("--schema-only")
.arg(connstr.as_str())
.stdout(Stdio::piped())
.stderr(Stdio::piped())
.kill_on_drop(true)

View File

@@ -1,16 +1,43 @@
use anyhow::{anyhow, Ok, Result};
use postgres::Client;
use tokio_postgres::NoTls;
use tracing::{error, instrument, warn};
use crate::compute::ComputeNode;
/// Create a special service table for availability checks
/// only if it does not exist already.
pub fn create_availability_check_data(client: &mut Client) -> Result<()> {
let query = "
DO $$
BEGIN
IF NOT EXISTS(
SELECT 1
FROM pg_catalog.pg_tables
WHERE tablename = 'health_check'
)
THEN
CREATE TABLE health_check (
id serial primary key,
updated_at timestamptz default now()
);
INSERT INTO health_check VALUES (1, now())
ON CONFLICT (id) DO UPDATE
SET updated_at = now();
END IF;
END
$$;";
client.execute(query, &[])?;
Ok(())
}
/// Update timestamp in a row in a special service table to check
/// that we can actually write some data in this particular timeline.
#[instrument(skip_all)]
pub async fn check_writability(compute: &ComputeNode) -> Result<()> {
// Connect to the database.
let conf = compute.get_tokio_conn_conf(Some("compute_ctl:availability_checker"));
let (client, connection) = conf.connect(NoTls).await?;
let (client, connection) = tokio_postgres::connect(compute.connstr.as_str(), NoTls).await?;
if client.is_closed() {
return Err(anyhow!("connection to postgres closed"));
}

View File

@@ -1,28 +1,26 @@
use std::collections::{HashMap, HashSet};
use std::collections::HashMap;
use std::env;
use std::fs;
use std::iter::once;
use std::os::unix::fs::{symlink, PermissionsExt};
use std::path::Path;
use std::process::{Command, Stdio};
use std::str::FromStr;
use std::sync::atomic::AtomicU32;
use std::sync::atomic::Ordering;
use std::sync::{Arc, Condvar, Mutex, RwLock};
use std::sync::{Condvar, Mutex, RwLock};
use std::thread;
use std::time::Duration;
use std::time::Instant;
use anyhow::{Context, Result};
use chrono::{DateTime, Utc};
use compute_api::spec::{Database, PgIdent, Role};
use compute_api::spec::PgIdent;
use futures::future::join_all;
use futures::stream::FuturesUnordered;
use futures::StreamExt;
use nix::unistd::Pid;
use postgres;
use postgres::error::SqlState;
use postgres::NoTls;
use postgres::{Client, NoTls};
use tracing::{debug, error, info, instrument, warn};
use utils::id::{TenantId, TimelineId};
use utils::lsn::Lsn;
@@ -33,24 +31,15 @@ use compute_api::spec::{ComputeFeature, ComputeMode, ComputeSpec, ExtVersion};
use utils::measured_stream::MeasuredReader;
use nix::sys::signal::{kill, Signal};
use remote_storage::{DownloadError, RemotePath};
use tokio::spawn;
use crate::installed_extensions::get_installed_extensions;
use remote_storage::{DownloadError, RemotePath};
use crate::checker::create_availability_check_data;
use crate::installed_extensions::get_installed_extensions_sync;
use crate::local_proxy;
use crate::logger::inlinify;
use crate::pg_helpers::*;
use crate::spec::*;
use crate::spec_apply::ApplySpecPhase::{
CreateAndAlterDatabases, CreateAndAlterRoles, CreateAvailabilityCheck, CreateSchemaNeon,
CreateSuperUser, DropInvalidDatabases, DropRoles, FinalizeDropLogicalSubscriptions,
HandleNeonExtension, HandleOtherExtensions, RenameAndDeleteDatabases, RenameRoles,
RunInEachDatabase,
};
use crate::spec_apply::PerDatabasePhase;
use crate::spec_apply::PerDatabasePhase::{
ChangeSchemaPerms, DeleteDBRoleReferences, DropLogicalSubscriptions, HandleAnonExtension,
};
use crate::spec_apply::{apply_operations, MutableApplyContext, DB};
use crate::sync_sk::{check_if_synced, ping_safekeeper};
use crate::{config, extension_server};
@@ -61,10 +50,6 @@ pub static PG_PID: AtomicU32 = AtomicU32::new(0);
pub struct ComputeNode {
// Url type maintains proper escaping
pub connstr: url::Url,
// We connect to Postgres from many different places, so build configs once
// and reuse them where needed.
pub conn_conf: postgres::config::Config,
pub tokio_conn_conf: tokio_postgres::config::Config,
pub pgdata: String,
pub pgbin: String,
pub pgversion: String,
@@ -81,8 +66,6 @@ pub struct ComputeNode {
/// - we push spec and it does configuration
/// - but then it is restarted without any spec again
pub live_config_allowed: bool,
/// The port that the compute's HTTP server listens on
pub http_port: u16,
/// Volatile part of the `ComputeNode`, which should be used under `Mutex`.
/// To allow HTTP API server to serving status requests, while configuration
/// is in progress, lock should be held only for short periods of time to do
@@ -241,7 +224,10 @@ fn maybe_cgexec(cmd: &str) -> Command {
}
}
pub(crate) fn construct_superuser_query(spec: &ComputeSpec) -> String {
/// Create special neon_superuser role, that's a slightly nerfed version of a real superuser
/// that we give to customers
#[instrument(skip_all)]
fn create_neon_superuser(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
let roles = spec
.cluster
.roles
@@ -310,8 +296,11 @@ pub(crate) fn construct_superuser_query(spec: &ComputeSpec) -> String {
$$;"#,
roles_decl, database_decl,
);
query
info!("Neon superuser created: {}", inlinify(&query));
client
.simple_query(&query)
.map_err(|e| anyhow::anyhow!(e).context(query))?;
Ok(())
}
impl ComputeNode {
@@ -340,15 +329,6 @@ impl ComputeNode {
self.state.lock().unwrap().status
}
pub fn get_timeline_id(&self) -> Option<TimelineId> {
self.state
.lock()
.unwrap()
.pspec
.as_ref()
.map(|s| s.timeline_id)
}
// Remove `pgdata` directory and create it again with right permissions.
fn create_pgdata(&self) -> Result<()> {
// Ignore removal error, likely it is a 'No such file or directory (os error 2)'.
@@ -624,7 +604,11 @@ impl ComputeNode {
/// Do all the preparations like PGDATA directory creation, configuration,
/// safekeepers sync, basebackup, etc.
#[instrument(skip_all)]
pub fn prepare_pgdata(&self, compute_state: &ComputeState) -> Result<()> {
pub fn prepare_pgdata(
&self,
compute_state: &ComputeState,
extension_server_port: u16,
) -> Result<()> {
let pspec = compute_state.pspec.as_ref().expect("spec must be set");
let spec = &pspec.spec;
let pgdata_path = Path::new(&self.pgdata);
@@ -634,7 +618,7 @@ impl ComputeNode {
config::write_postgres_conf(
&pgdata_path.join("postgresql.conf"),
&pspec.spec,
self.http_port,
Some(extension_server_port),
)?;
// Syncing safekeepers is only safe with primary nodes: if a primary
@@ -814,10 +798,10 @@ impl ComputeNode {
/// version. In the future, it may upgrade all 3rd-party extensions.
#[instrument(skip_all)]
pub fn post_apply_config(&self) -> Result<()> {
let conf = self.get_conn_conf(Some("compute_ctl:post_apply_config"));
let connstr = self.connstr.clone();
thread::spawn(move || {
let func = || {
let mut client = conf.connect(NoTls)?;
let mut client = Client::connect(connstr.as_str(), NoTls)?;
handle_neon_extension_upgrade(&mut client)
.context("handle_neon_extension_upgrade")?;
Ok::<_, anyhow::Error>(())
@@ -829,51 +813,40 @@ impl ComputeNode {
Ok(())
}
pub fn get_conn_conf(&self, application_name: Option<&str>) -> postgres::Config {
let mut conf = self.conn_conf.clone();
if let Some(application_name) = application_name {
conf.application_name(application_name);
}
conf
}
/// Do initial configuration of the already started Postgres.
#[instrument(skip_all)]
pub fn apply_config(&self, compute_state: &ComputeState) -> Result<()> {
// If connection fails,
// it may be the old node with `zenith_admin` superuser.
//
// In this case we need to connect with old `zenith_admin` name
// and create new user. We cannot simply rename connected user,
// but we can create a new one and grant it all privileges.
let mut connstr = self.connstr.clone();
connstr
.query_pairs_mut()
.append_pair("application_name", "apply_config");
pub fn get_tokio_conn_conf(&self, application_name: Option<&str>) -> tokio_postgres::Config {
let mut conf = self.tokio_conn_conf.clone();
if let Some(application_name) = application_name {
conf.application_name(application_name);
}
conf
}
pub async fn get_maintenance_client(
conf: &tokio_postgres::Config,
) -> Result<tokio_postgres::Client> {
let mut conf = conf.clone();
conf.application_name("compute_ctl:apply_config");
let (client, conn) = match conf.connect(NoTls).await {
// If connection fails, it may be the old node with `zenith_admin` superuser.
//
// In this case we need to connect with old `zenith_admin` name
// and create new user. We cannot simply rename connected user,
// but we can create a new one and grant it all privileges.
let mut client = match Client::connect(connstr.as_str(), NoTls) {
Err(e) => match e.code() {
Some(&SqlState::INVALID_PASSWORD)
| Some(&SqlState::INVALID_AUTHORIZATION_SPECIFICATION) => {
// Connect with zenith_admin if cloud_admin could not authenticate
// connect with zenith_admin if cloud_admin could not authenticate
info!(
"cannot connect to postgres: {}, retrying with `zenith_admin` username",
e
);
let mut zenith_admin_conf = postgres::config::Config::from(conf.clone());
zenith_admin_conf.application_name("compute_ctl:apply_config");
zenith_admin_conf.user("zenith_admin");
let mut zenith_admin_connstr = connstr.clone();
zenith_admin_connstr
.set_username("zenith_admin")
.map_err(|_| anyhow::anyhow!("invalid connstr"))?;
let mut client =
zenith_admin_conf.connect(NoTls)
Client::connect(zenith_admin_connstr.as_str(), NoTls)
.context("broken cloud_admin credential: tried connecting with cloud_admin but could not authenticate, and zenith_admin does not work either")?;
// Disable forwarding so that users don't get a cloud_admin role
let mut func = || {
client.simple_query("SET neon.forward_ddl = false")?;
client.simple_query("CREATE USER cloud_admin WITH SUPERUSER")?;
@@ -884,462 +857,58 @@ impl ComputeNode {
drop(client);
// Reconnect with connstring with expected name
conf.connect(NoTls).await?
// reconnect with connstring with expected name
Client::connect(connstr.as_str(), NoTls)?
}
_ => return Err(e.into()),
},
Ok((client, conn)) => (client, conn),
Ok(client) => client,
};
spawn(async move {
if let Err(e) = conn.await {
error!("maintenance client connection error: {}", e);
}
});
// Disable DDL forwarding because control plane already knows about the roles/databases
// we're about to modify.
// Disable DDL forwarding because control plane already knows about these roles/databases.
client
.simple_query("SET neon.forward_ddl = false")
.await
.context("apply_config SET neon.forward_ddl = false")?;
Ok(client)
}
// Proceed with post-startup configuration. Note, that order of operations is important.
let spec = &compute_state.pspec.as_ref().expect("spec must be set").spec;
create_neon_superuser(spec, &mut client).context("apply_config create_neon_superuser")?;
cleanup_instance(&mut client).context("apply_config cleanup_instance")?;
handle_roles(spec, &mut client).context("apply_config handle_roles")?;
handle_databases(spec, &mut client).context("apply_config handle_databases")?;
handle_role_deletions(spec, connstr.as_str(), &mut client)
.context("apply_config handle_role_deletions")?;
handle_grants(
spec,
&mut client,
connstr.as_str(),
self.has_feature(ComputeFeature::AnonExtension),
)
.context("apply_config handle_grants")?;
handle_extensions(spec, &mut client).context("apply_config handle_extensions")?;
handle_extension_neon(&mut client).context("apply_config handle_extension_neon")?;
create_availability_check_data(&mut client)
.context("apply_config create_availability_check_data")?;
/// Apply the spec to the running PostgreSQL instance.
/// The caller can decide to run with multiple clients in parallel, or
/// single mode. Either way, the commands executed will be the same, and
/// only commands run in different databases are parallelized.
#[instrument(skip_all)]
pub fn apply_spec_sql(
&self,
spec: Arc<ComputeSpec>,
conf: Arc<tokio_postgres::Config>,
concurrency: usize,
) -> Result<()> {
let rt = tokio::runtime::Builder::new_multi_thread()
.enable_all()
.build()?;
// 'Close' connection
drop(client);
info!("Applying config with max {} concurrency", concurrency);
debug!("Config: {:?}", spec);
rt.block_on(async {
// Proceed with post-startup configuration. Note, that order of operations is important.
let client = Self::get_maintenance_client(&conf).await?;
let spec = spec.clone();
let databases = get_existing_dbs_async(&client).await?;
let roles = get_existing_roles_async(&client)
.await?
.into_iter()
.map(|role| (role.name.clone(), role))
.collect::<HashMap<String, Role>>();
// Check if we need to drop subscriptions before starting the endpoint.
//
// It is important to do this operation exactly once when endpoint starts on a new branch.
// Otherwise, we may drop not inherited, but newly created subscriptions.
//
// We cannot rely only on spec.drop_subscriptions_before_start flag,
// because if for some reason compute restarts inside VM,
// it will start again with the same spec and flag value.
//
// To handle this, we save the fact of the operation in the database
// in the neon.drop_subscriptions_done table.
// If the table does not exist, we assume that the operation was never performed, so we must do it.
// If table exists, we check if the operation was performed on the current timelilne.
//
let mut drop_subscriptions_done = false;
if spec.drop_subscriptions_before_start {
let timeline_id = self.get_timeline_id().context("timeline_id must be set")?;
let query = format!("select 1 from neon.drop_subscriptions_done where timeline_id = '{}'", timeline_id);
info!("Checking if drop subscription operation was already performed for timeline_id: {}", timeline_id);
drop_subscriptions_done = match
client.simple_query(&query).await {
Ok(result) => {
matches!(&result[0], postgres::SimpleQueryMessage::Row(_))
},
Err(e) =>
{
match e.code() {
Some(&SqlState::UNDEFINED_TABLE) => false,
_ => {
// We don't expect any other error here, except for the schema/table not existing
error!("Error checking if drop subscription operation was already performed: {}", e);
return Err(e.into());
}
}
}
}
};
let jwks_roles = Arc::new(
spec.as_ref()
.local_proxy_config
.iter()
.flat_map(|it| &it.jwks)
.flatten()
.flat_map(|setting| &setting.role_names)
.cloned()
.collect::<HashSet<_>>(),
);
let ctx = Arc::new(tokio::sync::RwLock::new(MutableApplyContext {
roles,
dbs: databases,
}));
// Apply special pre drop database phase.
// NOTE: we use the code of RunInEachDatabase phase for parallelism
// and connection management, but we don't really run it in *each* database,
// only in databases, we're about to drop.
info!("Applying PerDatabase (pre-dropdb) phase");
let concurrency_token = Arc::new(tokio::sync::Semaphore::new(concurrency));
// Run the phase for each database that we're about to drop.
let db_processes = spec
.delta_operations
.iter()
.flatten()
.filter_map(move |op| {
if op.action.as_str() == "delete_db" {
Some(op.name.clone())
} else {
None
}
})
.map(|dbname| {
let spec = spec.clone();
let ctx = ctx.clone();
let jwks_roles = jwks_roles.clone();
let mut conf = conf.as_ref().clone();
let concurrency_token = concurrency_token.clone();
// We only need dbname field for this phase, so set other fields to dummy values
let db = DB::UserDB(Database {
name: dbname.clone(),
owner: "cloud_admin".to_string(),
options: None,
restrict_conn: false,
invalid: false,
});
debug!("Applying per-database phases for Database {:?}", &db);
match &db {
DB::SystemDB => {}
DB::UserDB(db) => {
conf.dbname(db.name.as_str());
}
}
let conf = Arc::new(conf);
let fut = Self::apply_spec_sql_db(
spec.clone(),
conf,
ctx.clone(),
jwks_roles.clone(),
concurrency_token.clone(),
db,
[DropLogicalSubscriptions].to_vec(),
);
Ok(spawn(fut))
})
.collect::<Vec<Result<_, anyhow::Error>>>();
for process in db_processes.into_iter() {
let handle = process?;
if let Err(e) = handle.await? {
// Handle the error case where the database does not exist
// We do not check whether the DB exists or not in the deletion phase,
// so we shouldn't be strict about it in pre-deletion cleanup as well.
if e.to_string().contains("does not exist") {
warn!("Error dropping subscription: {}", e);
} else {
return Err(e);
}
};
}
for phase in [
CreateSuperUser,
DropInvalidDatabases,
RenameRoles,
CreateAndAlterRoles,
RenameAndDeleteDatabases,
CreateAndAlterDatabases,
CreateSchemaNeon,
] {
info!("Applying phase {:?}", &phase);
apply_operations(
spec.clone(),
ctx.clone(),
jwks_roles.clone(),
phase,
|| async { Ok(&client) },
)
.await?;
}
info!("Applying RunInEachDatabase2 phase");
let concurrency_token = Arc::new(tokio::sync::Semaphore::new(concurrency));
let db_processes = spec
.cluster
.databases
.iter()
.map(|db| DB::new(db.clone()))
// include
.chain(once(DB::SystemDB))
.map(|db| {
let spec = spec.clone();
let ctx = ctx.clone();
let jwks_roles = jwks_roles.clone();
let mut conf = conf.as_ref().clone();
let concurrency_token = concurrency_token.clone();
let db = db.clone();
debug!("Applying per-database phases for Database {:?}", &db);
match &db {
DB::SystemDB => {}
DB::UserDB(db) => {
conf.dbname(db.name.as_str());
}
}
let conf = Arc::new(conf);
let mut phases = vec![
DeleteDBRoleReferences,
ChangeSchemaPerms,
HandleAnonExtension,
];
if spec.drop_subscriptions_before_start && !drop_subscriptions_done {
info!("Adding DropLogicalSubscriptions phase because drop_subscriptions_before_start is set");
phases.push(DropLogicalSubscriptions);
}
let fut = Self::apply_spec_sql_db(
spec.clone(),
conf,
ctx.clone(),
jwks_roles.clone(),
concurrency_token.clone(),
db,
phases,
);
Ok(spawn(fut))
})
.collect::<Vec<Result<_, anyhow::Error>>>();
for process in db_processes.into_iter() {
let handle = process?;
handle.await??;
}
let mut phases = vec![
HandleOtherExtensions,
HandleNeonExtension, // This step depends on CreateSchemaNeon
CreateAvailabilityCheck,
DropRoles,
];
// This step depends on CreateSchemaNeon
if spec.drop_subscriptions_before_start && !drop_subscriptions_done {
info!("Adding FinalizeDropLogicalSubscriptions phase because drop_subscriptions_before_start is set");
phases.push(FinalizeDropLogicalSubscriptions);
}
for phase in phases {
debug!("Applying phase {:?}", &phase);
apply_operations(
spec.clone(),
ctx.clone(),
jwks_roles.clone(),
phase,
|| async { Ok(&client) },
)
.await?;
}
Ok::<(), anyhow::Error>(())
})?;
Ok(())
}
/// Apply SQL migrations of the RunInEachDatabase phase.
///
/// May opt to not connect to databases that don't have any scheduled
/// operations. The function is concurrency-controlled with the provided
/// semaphore. The caller has to make sure the semaphore isn't exhausted.
async fn apply_spec_sql_db(
spec: Arc<ComputeSpec>,
conf: Arc<tokio_postgres::Config>,
ctx: Arc<tokio::sync::RwLock<MutableApplyContext>>,
jwks_roles: Arc<HashSet<String>>,
concurrency_token: Arc<tokio::sync::Semaphore>,
db: DB,
subphases: Vec<PerDatabasePhase>,
) -> Result<()> {
let _permit = concurrency_token.acquire().await?;
let mut client_conn = None;
for subphase in subphases {
apply_operations(
spec.clone(),
ctx.clone(),
jwks_roles.clone(),
RunInEachDatabase {
db: db.clone(),
subphase,
},
// Only connect if apply_operation actually wants a connection.
// It's quite possible this database doesn't need any queries,
// so by not connecting we save time and effort connecting to
// that database.
|| async {
if client_conn.is_none() {
let db_client = Self::get_maintenance_client(&conf).await?;
client_conn.replace(db_client);
}
let client = client_conn.as_ref().unwrap();
Ok(client)
},
)
.await?;
}
drop(client_conn);
Ok::<(), anyhow::Error>(())
}
/// Choose how many concurrent connections to use for applying the spec changes.
pub fn max_service_connections(
&self,
compute_state: &ComputeState,
spec: &ComputeSpec,
) -> usize {
// If the cluster is in Init state we don't have to deal with user connections,
// and can thus use all `max_connections` connection slots. However, that's generally not
// very efficient, so we generally still limit it to a smaller number.
if compute_state.status == ComputeStatus::Init {
// If the settings contain 'max_connections', use that as template
if let Some(config) = spec.cluster.settings.find("max_connections") {
config.parse::<usize>().ok()
} else {
// Otherwise, try to find the setting in the postgresql_conf string
spec.cluster
.postgresql_conf
.iter()
.flat_map(|conf| conf.split("\n"))
.filter_map(|line| {
if !line.contains("max_connections") {
return None;
}
let (key, value) = line.split_once("=")?;
let key = key
.trim_start_matches(char::is_whitespace)
.trim_end_matches(char::is_whitespace);
let value = value
.trim_start_matches(char::is_whitespace)
.trim_end_matches(char::is_whitespace);
if key != "max_connections" {
return None;
}
value.parse::<usize>().ok()
})
.next()
}
// If max_connections is present, use at most 1/3rd of that.
// When max_connections is lower than 30, try to use at least 10 connections, but
// never more than max_connections.
.map(|limit| match limit {
0..10 => limit,
10..30 => 10,
30.. => limit / 3,
})
// If we didn't find max_connections, default to 10 concurrent connections.
.unwrap_or(10)
} else {
// state == Running
// Because the cluster is already in the Running state, we should assume users are
// already connected to the cluster, and high concurrency could negatively
// impact user connectivity. Therefore, we can limit concurrency to the number of
// reserved superuser connections, which users wouldn't be able to use anyway.
spec.cluster
.settings
.find("superuser_reserved_connections")
.iter()
.filter_map(|val| val.parse::<usize>().ok())
.map(|val| if val > 1 { val - 1 } else { 1 })
.last()
.unwrap_or(3)
}
}
/// Do initial configuration of the already started Postgres.
#[instrument(skip_all)]
pub fn apply_config(&self, compute_state: &ComputeState) -> Result<()> {
let conf = self.get_tokio_conn_conf(Some("compute_ctl:apply_config"));
let conf = Arc::new(conf);
let spec = Arc::new(
compute_state
.pspec
.as_ref()
.expect("spec must be set")
.spec
.clone(),
);
let max_concurrent_connections = self.max_service_connections(compute_state, &spec);
// Merge-apply spec & changes to PostgreSQL state.
self.apply_spec_sql(spec.clone(), conf.clone(), max_concurrent_connections)?;
if let Some(ref local_proxy) = &spec.clone().local_proxy_config {
if let Some(ref local_proxy) = spec.local_proxy_config {
info!("configuring local_proxy");
local_proxy::configure(local_proxy).context("apply_config local_proxy")?;
}
// Run migrations separately to not hold up cold starts
thread::spawn(move || {
let conf = conf.as_ref().clone();
let mut conf = postgres::config::Config::from(conf);
conf.application_name("compute_ctl:migrations");
let mut connstr = connstr.clone();
connstr
.query_pairs_mut()
.append_pair("application_name", "migrations");
match conf.connect(NoTls) {
Ok(mut client) => {
if let Err(e) = handle_migrations(&mut client) {
error!("Failed to run migrations: {}", e);
}
}
Err(e) => {
error!(
"Failed to connect to the compute for running migrations: {}",
e
);
}
};
let mut client = Client::connect(connstr.as_str(), NoTls)?;
handle_migrations(&mut client).context("apply_config handle_migrations")
});
Ok::<(), anyhow::Error>(())
Ok(())
}
// Wrapped this around `pg_ctl reload`, but right now we don't use
@@ -1395,26 +964,40 @@ impl ComputeNode {
// Write new config
let pgdata_path = Path::new(&self.pgdata);
let postgresql_conf_path = pgdata_path.join("postgresql.conf");
config::write_postgres_conf(&postgresql_conf_path, &spec, self.http_port)?;
let max_concurrent_connections = spec.reconfigure_concurrency;
// Temporarily reset max_cluster_size in config
config::write_postgres_conf(&postgresql_conf_path, &spec, None)?;
// temporarily reset max_cluster_size in config
// to avoid the possibility of hitting the limit, while we are reconfiguring:
// creating new extensions, roles, etc.
// creating new extensions, roles, etc...
config::with_compute_ctl_tmp_override(pgdata_path, "neon.max_cluster_size=-1", || {
self.pg_reload_conf()?;
let mut client = Client::connect(self.connstr.as_str(), NoTls)?;
// Proceed with post-startup configuration. Note, that order of operations is important.
// Disable DDL forwarding because control plane already knows about these roles/databases.
if spec.mode == ComputeMode::Primary {
let mut conf = tokio_postgres::Config::from_str(self.connstr.as_str()).unwrap();
conf.application_name("apply_config");
let conf = Arc::new(conf);
let spec = Arc::new(spec.clone());
self.apply_spec_sql(spec, conf, max_concurrent_connections)?;
client.simple_query("SET neon.forward_ddl = false")?;
cleanup_instance(&mut client)?;
handle_roles(&spec, &mut client)?;
handle_databases(&spec, &mut client)?;
handle_role_deletions(&spec, self.connstr.as_str(), &mut client)?;
handle_grants(
&spec,
&mut client,
self.connstr.as_str(),
self.has_feature(ComputeFeature::AnonExtension),
)?;
handle_extensions(&spec, &mut client)?;
handle_extension_neon(&mut client)?;
// We can skip handle_migrations here because a new migration can only appear
// if we have a new version of the compute_ctl binary, which can only happen
// if compute got restarted, in which case we'll end up inside of apply_config
// instead of reconfigure.
}
// 'Close' connection
drop(client);
Ok(())
})?;
@@ -1431,7 +1014,10 @@ impl ComputeNode {
}
#[instrument(skip_all)]
pub fn start_compute(&self) -> Result<(std::process::Child, std::thread::JoinHandle<()>)> {
pub fn start_compute(
&self,
extension_server_port: u16,
) -> Result<(std::process::Child, std::thread::JoinHandle<()>)> {
let compute_state = self.state.lock().unwrap().clone();
let pspec = compute_state.pspec.as_ref().expect("spec must be set");
info!(
@@ -1506,7 +1092,7 @@ impl ComputeNode {
info!("{:?}", remote_ext_metrics);
}
self.prepare_pgdata(&compute_state)?;
self.prepare_pgdata(&compute_state, extension_server_port)?;
let start_time = Utc::now();
let pg_process = self.start_postgres(pspec.storage_auth_token.clone())?;
@@ -1529,31 +1115,13 @@ impl ComputeNode {
Ok(())
},
)?;
let postgresql_conf_path = pgdata_path.join("postgresql.conf");
if config::line_in_file(
&postgresql_conf_path,
"neon.disable_logical_replication_subscribers=false",
)? {
info!("updated postgresql.conf to set neon.disable_logical_replication_subscribers=false");
}
self.pg_reload_conf()?;
}
self.post_apply_config()?;
let conf = self.get_conn_conf(None);
let connstr = self.connstr.clone();
thread::spawn(move || {
let res = get_installed_extensions(conf);
match res {
Ok(extensions) => {
info!(
"[NEON_EXT_STAT] {}",
serde_json::to_string(&extensions)
.expect("failed to serialize extensions list")
);
}
Err(err) => error!("could not get installed extensions: {err:?}"),
}
get_installed_extensions_sync(connstr).context("get_installed_extensions")
});
}
@@ -1682,8 +1250,7 @@ impl ComputeNode {
/// Select `pg_stat_statements` data and return it as a stringified JSON
pub async fn collect_insights(&self) -> String {
let mut result_rows: Vec<String> = Vec::new();
let conf = self.get_tokio_conn_conf(Some("compute_ctl:collect_insights"));
let connect_result = conf.connect(NoTls).await;
let connect_result = tokio_postgres::connect(self.connstr.as_str(), NoTls).await;
let (client, connection) = connect_result.unwrap();
tokio::spawn(async move {
if let Err(e) = connection.await {
@@ -1809,9 +1376,10 @@ LIMIT 100",
privileges: &[Privilege],
role_name: &PgIdent,
) -> Result<()> {
use tokio_postgres::config::Config;
use tokio_postgres::NoTls;
let mut conf = self.get_tokio_conn_conf(Some("compute_ctl:set_role_grants"));
let mut conf = Config::from_str(self.connstr.as_str()).unwrap();
conf.dbname(db_name);
let (db_client, conn) = conf
@@ -1848,9 +1416,10 @@ LIMIT 100",
db_name: &PgIdent,
ext_version: ExtVersion,
) -> Result<ExtVersion> {
use tokio_postgres::config::Config;
use tokio_postgres::NoTls;
let mut conf = self.get_tokio_conn_conf(Some("compute_ctl:install_extension"));
let mut conf = Config::from_str(self.connstr.as_str()).unwrap();
conf.dbname(db_name);
let (db_client, conn) = conf

View File

@@ -37,7 +37,7 @@ pub fn line_in_file(path: &Path, line: &str) -> Result<bool> {
pub fn write_postgres_conf(
path: &Path,
spec: &ComputeSpec,
extension_server_port: u16,
extension_server_port: Option<u16>,
) -> Result<()> {
// File::create() destroys the file content if it exists.
let mut file = File::create(path)?;
@@ -116,7 +116,7 @@ pub fn write_postgres_conf(
vartype: "enum".to_owned(),
};
writeln!(file, "{}", opt.to_pg_setting())?;
write!(file, "{}", opt.to_pg_setting())?;
}
}
@@ -127,13 +127,8 @@ pub fn write_postgres_conf(
writeln!(file, "# Managed by compute_ctl: end")?;
}
writeln!(file, "neon.extension_server_port={}", extension_server_port)?;
if spec.drop_subscriptions_before_start {
writeln!(file, "neon.disable_logical_replication_subscribers=true")?;
} else {
// be explicit about the default value
writeln!(file, "neon.disable_logical_replication_subscribers=false")?;
if let Some(port) = extension_server_port {
writeln!(file, "neon.extension_server_port={}", port)?;
}
// This is essential to keep this line at the end of the file,

View File

@@ -85,8 +85,6 @@ use tracing::info;
use tracing::log::warn;
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`
@@ -105,33 +103,14 @@ fn get_pg_config(argument: &str, pgbin: &str) -> String {
.to_string()
}
pub fn get_pg_version(pgbin: &str) -> PostgresMajorVersion {
pub fn get_pg_version(pgbin: &str) -> String {
// 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);
parse_pg_version(&human_version)
parse_pg_version(&human_version).to_string()
}
pub fn get_pg_version_string(pgbin: &str) -> String {
match get_pg_version(pgbin) {
PostgresMajorVersion::V14 => "v14",
PostgresMajorVersion::V15 => "v15",
PostgresMajorVersion::V16 => "v16",
PostgresMajorVersion::V17 => "v17",
}
.to_owned()
}
#[derive(Copy, Clone, Debug, PartialEq, Eq)]
pub enum PostgresMajorVersion {
V14,
V15,
V16,
V17,
}
fn parse_pg_version(human_version: &str) -> PostgresMajorVersion {
use PostgresMajorVersion::*;
fn parse_pg_version(human_version: &str) -> &str {
// 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
@@ -142,10 +121,10 @@ fn parse_pg_version(human_version: &str) -> PostgresMajorVersion {
.captures(human_version)
{
Some(captures) if captures.len() == 2 => match &captures["major"] {
"14" => return V14,
"15" => return V15,
"16" => return V16,
"17" => return V17,
"14" => return "v14",
"15" => return "v15",
"16" => return "v16",
"17" => return "v17",
_ => {}
},
_ => {}
@@ -258,60 +237,23 @@ pub fn create_control_files(remote_extensions: &RemoteExtSpec, pgbin: &str) {
async fn download_extension_tar(ext_remote_storage: &str, ext_path: &str) -> Result<Bytes> {
let uri = format!("{}/{}", ext_remote_storage, ext_path);
info!("Download extension {} from uri {}", ext_path, uri);
info!("Download extension {:?} from uri {:?}", ext_path, uri);
match do_extension_server_request(&uri).await {
Ok(resp) => {
info!("Successfully downloaded remote extension data {}", ext_path);
REMOTE_EXT_REQUESTS_TOTAL
.with_label_values(&[&StatusCode::OK.to_string()])
.inc();
Ok(resp)
}
Err((msg, status)) => {
REMOTE_EXT_REQUESTS_TOTAL
.with_label_values(&[&status])
.inc();
bail!(msg);
}
}
}
let resp = reqwest::get(uri).await?;
// Do a single remote extensions server request.
// Return result or (error message + stringified status code) in case of any failures.
async fn do_extension_server_request(uri: &str) -> Result<Bytes, (String, String)> {
let resp = reqwest::get(uri).await.map_err(|e| {
(
format!(
"could not perform remote extensions server request: {:?}",
e
),
UNKNOWN_HTTP_STATUS.to_string(),
)
})?;
let status = resp.status();
match status {
match resp.status() {
StatusCode::OK => match resp.bytes().await {
Ok(resp) => Ok(resp),
Err(e) => Err((
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(),
)),
Ok(resp) => {
info!("Download extension {:?} completed successfully", ext_path);
Ok(resp)
}
Err(e) => bail!("could not deserialize remote extension response: {}", e),
},
StatusCode::SERVICE_UNAVAILABLE => Err((
"remote extensions server is temporarily unavailable".to_string(),
status.to_string(),
)),
_ => Err((
format!(
"unexpected remote extensions server response status code: {}",
status
),
status.to_string(),
)),
StatusCode::SERVICE_UNAVAILABLE => bail!("remote extension is temporarily unavailable"),
_ => bail!(
"unexpected remote extension response status code: {}",
resp.status()
),
}
}
@@ -321,25 +263,24 @@ mod tests {
#[test]
fn test_parse_pg_version() {
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"), "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)"),
V15
"v15"
);
assert_eq!(parse_pg_version("PostgreSQL 14.15"), V14);
assert_eq!(parse_pg_version("PostgreSQL 14.0"), V14);
assert_eq!(parse_pg_version("PostgreSQL 14.15"), "v14");
assert_eq!(parse_pg_version("PostgreSQL 14.0"), "v14");
assert_eq!(
parse_pg_version("PostgreSQL 14.9 (Debian 14.9-1.pgdg120+1"),
V14
"v14"
);
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);
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

@@ -0,0 +1,574 @@
use std::convert::Infallible;
use std::net::IpAddr;
use std::net::Ipv6Addr;
use std::net::SocketAddr;
use std::sync::Arc;
use std::thread;
use crate::catalog::SchemaDumpError;
use crate::catalog::{get_database_schema, get_dbs_and_roles};
use crate::compute::forward_termination_signal;
use crate::compute::{ComputeNode, ComputeState, ParsedSpec};
use crate::installed_extensions;
use compute_api::requests::{ConfigurationRequest, ExtensionInstallRequest, SetRoleGrantsRequest};
use compute_api::responses::{
ComputeStatus, ComputeStatusResponse, ExtensionInstallResult, GenericAPIError,
SetRoleGrantsResponse,
};
use anyhow::Result;
use hyper::header::CONTENT_TYPE;
use hyper::service::{make_service_fn, service_fn};
use hyper::{Body, Method, Request, Response, Server, StatusCode};
use metrics::Encoder;
use metrics::TextEncoder;
use tokio::task;
use tracing::{debug, error, info, warn};
use tracing_utils::http::OtelName;
use utils::http::request::must_get_query_param;
fn status_response_from_state(state: &ComputeState) -> ComputeStatusResponse {
ComputeStatusResponse {
start_time: state.start_time,
tenant: state
.pspec
.as_ref()
.map(|pspec| pspec.tenant_id.to_string()),
timeline: state
.pspec
.as_ref()
.map(|pspec| pspec.timeline_id.to_string()),
status: state.status,
last_active: state.last_active,
error: state.error.clone(),
}
}
// Service function to handle all available routes.
async fn routes(req: Request<Body>, compute: &Arc<ComputeNode>) -> Response<Body> {
//
// NOTE: The URI path is currently included in traces. That's OK because
// it doesn't contain any variable parts or sensitive information. But
// please keep that in mind if you change the routing here.
//
match (req.method(), req.uri().path()) {
// Serialized compute state.
(&Method::GET, "/status") => {
debug!("serving /status GET request");
let state = compute.state.lock().unwrap();
let status_response = status_response_from_state(&state);
Response::new(Body::from(serde_json::to_string(&status_response).unwrap()))
}
// Startup metrics in JSON format. Keep /metrics reserved for a possible
// future use for Prometheus metrics format.
(&Method::GET, "/metrics.json") => {
info!("serving /metrics.json GET request");
let metrics = compute.state.lock().unwrap().metrics.clone();
Response::new(Body::from(serde_json::to_string(&metrics).unwrap()))
}
// Prometheus metrics
(&Method::GET, "/metrics") => {
debug!("serving /metrics GET request");
let mut buffer = vec![];
let metrics = installed_extensions::collect();
let encoder = TextEncoder::new();
encoder.encode(&metrics, &mut buffer).unwrap();
match Response::builder()
.status(StatusCode::OK)
.header(CONTENT_TYPE, encoder.format_type())
.body(Body::from(buffer))
{
Ok(response) => response,
Err(err) => {
let msg = format!("error handling /metrics request: {err}");
error!(msg);
render_json_error(&msg, StatusCode::INTERNAL_SERVER_ERROR)
}
}
}
// Collect Postgres current usage insights
(&Method::GET, "/insights") => {
info!("serving /insights GET request");
let status = compute.get_status();
if status != ComputeStatus::Running {
let msg = format!("compute is not running, current status: {:?}", status);
error!(msg);
return Response::new(Body::from(msg));
}
let insights = compute.collect_insights().await;
Response::new(Body::from(insights))
}
(&Method::POST, "/check_writability") => {
info!("serving /check_writability POST request");
let status = compute.get_status();
if status != ComputeStatus::Running {
let msg = format!(
"invalid compute status for check_writability request: {:?}",
status
);
error!(msg);
return Response::new(Body::from(msg));
}
let res = crate::checker::check_writability(compute).await;
match res {
Ok(_) => Response::new(Body::from("true")),
Err(e) => {
error!("check_writability failed: {}", e);
Response::new(Body::from(e.to_string()))
}
}
}
(&Method::POST, "/extensions") => {
info!("serving /extensions POST request");
let status = compute.get_status();
if status != ComputeStatus::Running {
let msg = format!(
"invalid compute status for extensions request: {:?}",
status
);
error!(msg);
return render_json_error(&msg, StatusCode::PRECONDITION_FAILED);
}
let request = hyper::body::to_bytes(req.into_body()).await.unwrap();
let request = serde_json::from_slice::<ExtensionInstallRequest>(&request).unwrap();
let res = compute
.install_extension(&request.extension, &request.database, request.version)
.await;
match res {
Ok(version) => render_json(Body::from(
serde_json::to_string(&ExtensionInstallResult {
extension: request.extension,
version,
})
.unwrap(),
)),
Err(e) => {
error!("install_extension failed: {}", e);
render_json_error(&e.to_string(), StatusCode::INTERNAL_SERVER_ERROR)
}
}
}
(&Method::GET, "/info") => {
let num_cpus = num_cpus::get_physical();
info!("serving /info GET request. num_cpus: {}", num_cpus);
Response::new(Body::from(
serde_json::json!({
"num_cpus": num_cpus,
})
.to_string(),
))
}
// Accept spec in JSON format and request compute configuration. If
// anything goes wrong after we set the compute status to `ConfigurationPending`
// and update compute state with new spec, we basically leave compute
// in the potentially wrong state. That said, it's control-plane's
// responsibility to watch compute state after reconfiguration request
// and to clean restart in case of errors.
(&Method::POST, "/configure") => {
info!("serving /configure POST request");
match handle_configure_request(req, compute).await {
Ok(msg) => Response::new(Body::from(msg)),
Err((msg, code)) => {
error!("error handling /configure request: {msg}");
render_json_error(&msg, code)
}
}
}
(&Method::POST, "/terminate") => {
info!("serving /terminate POST request");
match handle_terminate_request(compute).await {
Ok(()) => Response::new(Body::empty()),
Err((msg, code)) => {
error!("error handling /terminate request: {msg}");
render_json_error(&msg, code)
}
}
}
(&Method::GET, "/dbs_and_roles") => {
info!("serving /dbs_and_roles GET request",);
match get_dbs_and_roles(compute).await {
Ok(res) => render_json(Body::from(serde_json::to_string(&res).unwrap())),
Err(_) => {
render_json_error("can't get dbs and roles", StatusCode::INTERNAL_SERVER_ERROR)
}
}
}
(&Method::GET, "/database_schema") => {
let database = match must_get_query_param(&req, "database") {
Err(e) => return e.into_response(),
Ok(database) => database,
};
info!("serving /database_schema GET request with database: {database}",);
match get_database_schema(compute, &database).await {
Ok(res) => render_plain(Body::wrap_stream(res)),
Err(SchemaDumpError::DatabaseDoesNotExist) => {
render_json_error("database does not exist", StatusCode::NOT_FOUND)
}
Err(e) => {
error!("can't get schema dump: {}", e);
render_json_error("can't get schema dump", StatusCode::INTERNAL_SERVER_ERROR)
}
}
}
(&Method::POST, "/grants") => {
info!("serving /grants POST request");
let status = compute.get_status();
if status != ComputeStatus::Running {
let msg = format!(
"invalid compute status for set_role_grants request: {:?}",
status
);
error!(msg);
return render_json_error(&msg, StatusCode::PRECONDITION_FAILED);
}
let request = hyper::body::to_bytes(req.into_body()).await.unwrap();
let request = serde_json::from_slice::<SetRoleGrantsRequest>(&request).unwrap();
let res = compute
.set_role_grants(
&request.database,
&request.schema,
&request.privileges,
&request.role,
)
.await;
match res {
Ok(()) => render_json(Body::from(
serde_json::to_string(&SetRoleGrantsResponse {
database: request.database,
schema: request.schema,
role: request.role,
privileges: request.privileges,
})
.unwrap(),
)),
Err(e) => render_json_error(
&format!("could not grant role privileges to the schema: {e}"),
// TODO: can we filter on role/schema not found errors
// and return appropriate error code?
StatusCode::INTERNAL_SERVER_ERROR,
),
}
}
// get the list of installed extensions
// currently only used in python tests
// TODO: call it from cplane
(&Method::GET, "/installed_extensions") => {
info!("serving /installed_extensions GET request");
let status = compute.get_status();
if status != ComputeStatus::Running {
let msg = format!(
"invalid compute status for extensions request: {:?}",
status
);
error!(msg);
return Response::new(Body::from(msg));
}
let connstr = compute.connstr.clone();
let res = crate::installed_extensions::get_installed_extensions(connstr).await;
match res {
Ok(res) => render_json(Body::from(serde_json::to_string(&res).unwrap())),
Err(e) => render_json_error(
&format!("could not get list of installed extensions: {}", e),
StatusCode::INTERNAL_SERVER_ERROR,
),
}
}
// download extension files from remote extension storage on demand
(&Method::POST, route) if route.starts_with("/extension_server/") => {
info!("serving {:?} POST request", route);
info!("req.uri {:?}", req.uri());
// don't even try to download extensions
// if no remote storage is configured
if compute.ext_remote_storage.is_none() {
info!("no extensions remote storage configured");
let mut resp = Response::new(Body::from("no remote storage configured"));
*resp.status_mut() = StatusCode::INTERNAL_SERVER_ERROR;
return resp;
}
let mut is_library = false;
if let Some(params) = req.uri().query() {
info!("serving {:?} POST request with params: {}", route, params);
if params == "is_library=true" {
is_library = true;
} else {
let mut resp = Response::new(Body::from("Wrong request parameters"));
*resp.status_mut() = StatusCode::BAD_REQUEST;
return resp;
}
}
let filename = route.split('/').last().unwrap().to_string();
info!("serving /extension_server POST request, filename: {filename:?} is_library: {is_library}");
// get ext_name and path from spec
// don't lock compute_state for too long
let ext = {
let compute_state = compute.state.lock().unwrap();
let pspec = compute_state.pspec.as_ref().expect("spec must be set");
let spec = &pspec.spec;
// debug only
info!("spec: {:?}", spec);
let remote_extensions = match spec.remote_extensions.as_ref() {
Some(r) => r,
None => {
info!("no remote extensions spec was provided");
let mut resp = Response::new(Body::from("no remote storage configured"));
*resp.status_mut() = StatusCode::INTERNAL_SERVER_ERROR;
return resp;
}
};
remote_extensions.get_ext(
&filename,
is_library,
&compute.build_tag,
&compute.pgversion,
)
};
match ext {
Ok((ext_name, ext_path)) => {
match compute.download_extension(ext_name, ext_path).await {
Ok(_) => Response::new(Body::from("OK")),
Err(e) => {
error!("extension download failed: {}", e);
let mut resp = Response::new(Body::from(e.to_string()));
*resp.status_mut() = StatusCode::INTERNAL_SERVER_ERROR;
resp
}
}
}
Err(e) => {
warn!("extension download failed to find extension: {}", e);
let mut resp = Response::new(Body::from("failed to find file"));
*resp.status_mut() = StatusCode::INTERNAL_SERVER_ERROR;
resp
}
}
}
// Return the `404 Not Found` for any other routes.
_ => {
let mut not_found = Response::new(Body::from("404 Not Found"));
*not_found.status_mut() = StatusCode::NOT_FOUND;
not_found
}
}
}
async fn handle_configure_request(
req: Request<Body>,
compute: &Arc<ComputeNode>,
) -> Result<String, (String, StatusCode)> {
if !compute.live_config_allowed {
return Err((
"live configuration is not allowed for this compute node".to_string(),
StatusCode::PRECONDITION_FAILED,
));
}
let body_bytes = hyper::body::to_bytes(req.into_body()).await.unwrap();
let spec_raw = String::from_utf8(body_bytes.to_vec()).unwrap();
if let Ok(request) = serde_json::from_str::<ConfigurationRequest>(&spec_raw) {
let spec = request.spec;
let parsed_spec = match ParsedSpec::try_from(spec) {
Ok(ps) => ps,
Err(msg) => return Err((msg, StatusCode::BAD_REQUEST)),
};
// XXX: wrap state update under lock in code blocks. Otherwise,
// we will try to `Send` `mut state` into the spawned thread
// bellow, which will cause error:
// ```
// error: future cannot be sent between threads safely
// ```
{
let mut state = compute.state.lock().unwrap();
if state.status != ComputeStatus::Empty && state.status != ComputeStatus::Running {
let msg = format!(
"invalid compute status for configuration request: {:?}",
state.status.clone()
);
return Err((msg, StatusCode::PRECONDITION_FAILED));
}
state.pspec = Some(parsed_spec);
state.set_status(ComputeStatus::ConfigurationPending, &compute.state_changed);
drop(state);
info!("set new spec and notified waiters");
}
// Spawn a blocking thread to wait for compute to become Running.
// This is needed to do not block the main pool of workers and
// be able to serve other requests while some particular request
// is waiting for compute to finish configuration.
let c = compute.clone();
task::spawn_blocking(move || {
let mut state = c.state.lock().unwrap();
while state.status != ComputeStatus::Running {
state = c.state_changed.wait(state).unwrap();
info!(
"waiting for compute to become Running, current status: {:?}",
state.status
);
if state.status == ComputeStatus::Failed {
let err = state.error.as_ref().map_or("unknown error", |x| x);
let msg = format!("compute configuration failed: {:?}", err);
return Err((msg, StatusCode::INTERNAL_SERVER_ERROR));
}
}
Ok(())
})
.await
.unwrap()?;
// Return current compute state if everything went well.
let state = compute.state.lock().unwrap().clone();
let status_response = status_response_from_state(&state);
Ok(serde_json::to_string(&status_response).unwrap())
} else {
Err(("invalid spec".to_string(), StatusCode::BAD_REQUEST))
}
}
fn render_json_error(e: &str, status: StatusCode) -> Response<Body> {
let error = GenericAPIError {
error: e.to_string(),
};
Response::builder()
.status(status)
.header(CONTENT_TYPE, "application/json")
.body(Body::from(serde_json::to_string(&error).unwrap()))
.unwrap()
}
fn render_json(body: Body) -> Response<Body> {
Response::builder()
.header(CONTENT_TYPE, "application/json")
.body(body)
.unwrap()
}
fn render_plain(body: Body) -> Response<Body> {
Response::builder()
.header(CONTENT_TYPE, "text/plain")
.body(body)
.unwrap()
}
async fn handle_terminate_request(compute: &Arc<ComputeNode>) -> Result<(), (String, StatusCode)> {
{
let mut state = compute.state.lock().unwrap();
if state.status == ComputeStatus::Terminated {
return Ok(());
}
if state.status != ComputeStatus::Empty && state.status != ComputeStatus::Running {
let msg = format!(
"invalid compute status for termination request: {}",
state.status
);
return Err((msg, StatusCode::PRECONDITION_FAILED));
}
state.set_status(ComputeStatus::TerminationPending, &compute.state_changed);
drop(state);
}
forward_termination_signal();
info!("sent signal and notified waiters");
// Spawn a blocking thread to wait for compute to become Terminated.
// This is needed to do not block the main pool of workers and
// be able to serve other requests while some particular request
// is waiting for compute to finish configuration.
let c = compute.clone();
task::spawn_blocking(move || {
let mut state = c.state.lock().unwrap();
while state.status != ComputeStatus::Terminated {
state = c.state_changed.wait(state).unwrap();
info!(
"waiting for compute to become {}, current status: {:?}",
ComputeStatus::Terminated,
state.status
);
}
Ok(())
})
.await
.unwrap()?;
info!("terminated Postgres");
Ok(())
}
// Main Hyper HTTP server function that runs it and blocks waiting on it forever.
#[tokio::main]
async fn serve(port: u16, state: Arc<ComputeNode>) {
// this usually binds to both IPv4 and IPv6 on linux
// see e.g. https://github.com/rust-lang/rust/pull/34440
let addr = SocketAddr::new(IpAddr::from(Ipv6Addr::UNSPECIFIED), port);
let make_service = make_service_fn(move |_conn| {
let state = state.clone();
async move {
Ok::<_, Infallible>(service_fn(move |req: Request<Body>| {
let state = state.clone();
async move {
Ok::<_, Infallible>(
// NOTE: We include the URI path in the string. It
// doesn't contain any variable parts or sensitive
// information in this API.
tracing_utils::http::tracing_handler(
req,
|req| routes(req, &state),
OtelName::UriPath,
)
.await,
)
}
}))
}
});
info!("starting HTTP server on {}", addr);
let server = Server::bind(&addr).serve(make_service);
// Run this server forever
if let Err(e) = server.await {
error!("server error: {}", e);
}
}
/// Launch a separate Hyper HTTP API server thread and return its `JoinHandle`.
pub fn launch_http_server(port: u16, state: &Arc<ComputeNode>) -> Result<thread::JoinHandle<()>> {
let state = Arc::clone(state);
Ok(thread::Builder::new()
.name("http-endpoint".into())
.spawn(move || serve(port, state))?)
}

View File

@@ -1,44 +0,0 @@
use std::ops::{Deref, DerefMut};
use axum::extract::{rejection::JsonRejection, FromRequest, Request};
use compute_api::responses::GenericAPIError;
use http::StatusCode;
/// Custom `Json` extractor, so that we can format errors into
/// `JsonResponse<GenericAPIError>`.
#[derive(Debug, Clone, Copy, Default)]
pub(crate) struct Json<T>(pub T);
impl<S, T> FromRequest<S> for Json<T>
where
axum::Json<T>: FromRequest<S, Rejection = JsonRejection>,
S: Send + Sync,
{
type Rejection = (StatusCode, axum::Json<GenericAPIError>);
async fn from_request(req: Request, state: &S) -> Result<Self, Self::Rejection> {
match axum::Json::<T>::from_request(req, state).await {
Ok(value) => Ok(Self(value.0)),
Err(rejection) => Err((
rejection.status(),
axum::Json(GenericAPIError {
error: rejection.body_text().to_lowercase(),
}),
)),
}
}
}
impl<T> Deref for Json<T> {
type Target = T;
fn deref(&self) -> &Self::Target {
&self.0
}
}
impl<T> DerefMut for Json<T> {
fn deref_mut(&mut self) -> &mut Self::Target {
&mut self.0
}
}

View File

@@ -1,7 +0,0 @@
pub(crate) mod json;
pub(crate) mod path;
pub(crate) mod query;
pub(crate) use json::Json;
pub(crate) use path::Path;
pub(crate) use query::Query;

View File

@@ -1,44 +0,0 @@
use std::ops::{Deref, DerefMut};
use axum::extract::{rejection::PathRejection, FromRequestParts};
use compute_api::responses::GenericAPIError;
use http::{request::Parts, StatusCode};
/// Custom `Path` extractor, so that we can format errors into
/// `JsonResponse<GenericAPIError>`.
#[derive(Debug, Clone, Copy, Default)]
pub(crate) struct Path<T>(pub T);
impl<S, T> FromRequestParts<S> for Path<T>
where
axum::extract::Path<T>: FromRequestParts<S, Rejection = PathRejection>,
S: Send + Sync,
{
type Rejection = (StatusCode, axum::Json<GenericAPIError>);
async fn from_request_parts(parts: &mut Parts, state: &S) -> Result<Self, Self::Rejection> {
match axum::extract::Path::<T>::from_request_parts(parts, state).await {
Ok(value) => Ok(Self(value.0)),
Err(rejection) => Err((
rejection.status(),
axum::Json(GenericAPIError {
error: rejection.body_text().to_ascii_lowercase(),
}),
)),
}
}
}
impl<T> Deref for Path<T> {
type Target = T;
fn deref(&self) -> &Self::Target {
&self.0
}
}
impl<T> DerefMut for Path<T> {
fn deref_mut(&mut self) -> &mut Self::Target {
&mut self.0
}
}

View File

@@ -1,44 +0,0 @@
use std::ops::{Deref, DerefMut};
use axum::extract::{rejection::QueryRejection, FromRequestParts};
use compute_api::responses::GenericAPIError;
use http::{request::Parts, StatusCode};
/// Custom `Query` extractor, so that we can format errors into
/// `JsonResponse<GenericAPIError>`.
#[derive(Debug, Clone, Copy, Default)]
pub(crate) struct Query<T>(pub T);
impl<S, T> FromRequestParts<S> for Query<T>
where
axum::extract::Query<T>: FromRequestParts<S, Rejection = QueryRejection>,
S: Send + Sync,
{
type Rejection = (StatusCode, axum::Json<GenericAPIError>);
async fn from_request_parts(parts: &mut Parts, state: &S) -> Result<Self, Self::Rejection> {
match axum::extract::Query::<T>::from_request_parts(parts, state).await {
Ok(value) => Ok(Self(value.0)),
Err(rejection) => Err((
rejection.status(),
axum::Json(GenericAPIError {
error: rejection.body_text().to_ascii_lowercase(),
}),
)),
}
}
}
impl<T> Deref for Query<T> {
type Target = T;
fn deref(&self) -> &Self::Target {
&self.0
}
}
impl<T> DerefMut for Query<T> {
fn deref_mut(&mut self) -> &mut Self::Target {
&mut self.0
}
}

View File

@@ -1,56 +1 @@
use axum::{body::Body, response::Response};
use compute_api::responses::{ComputeStatus, GenericAPIError};
use http::{header::CONTENT_TYPE, StatusCode};
use serde::Serialize;
use tracing::error;
pub use server::launch_http_server;
mod extract;
mod routes;
mod server;
/// Convenience response builder for JSON responses
struct JsonResponse;
impl JsonResponse {
/// Helper for actually creating a response
fn create_response(code: StatusCode, body: impl Serialize) -> Response {
Response::builder()
.status(code)
.header(CONTENT_TYPE.as_str(), "application/json")
.body(Body::from(serde_json::to_string(&body).unwrap()))
.unwrap()
}
/// Create a successful error response
pub(self) fn success(code: StatusCode, body: impl Serialize) -> Response {
assert!({
let code = code.as_u16();
(200..300).contains(&code)
});
Self::create_response(code, body)
}
/// Create an error response
pub(self) fn error(code: StatusCode, error: impl ToString) -> Response {
assert!(code.as_u16() >= 400);
let message = error.to_string();
error!(message);
Self::create_response(code, &GenericAPIError { error: message })
}
/// Create an error response related to the compute being in an invalid state
pub(self) fn invalid_status(status: ComputeStatus) -> Response {
Self::create_response(
StatusCode::PRECONDITION_FAILED,
&GenericAPIError {
error: format!("invalid compute status: {status}"),
},
)
}
}
pub mod api;

View File

@@ -37,7 +37,7 @@ paths:
schema:
$ref: "#/components/schemas/ComputeMetrics"
/metrics:
/metrics
get:
tags:
- Info
@@ -68,6 +68,35 @@ paths:
schema:
$ref: "#/components/schemas/ComputeInsights"
/installed_extensions:
get:
tags:
- Info
summary: Get installed extensions.
description: ""
operationId: getInstalledExtensions
responses:
200:
description: List of installed extensions
content:
application/json:
schema:
$ref: "#/components/schemas/InstalledExtensions"
/info:
get:
tags:
- Info
summary: Get info about the compute pod / VM.
description: ""
operationId: getInfo
responses:
200:
description: Info
content:
application/json:
schema:
$ref: "#/components/schemas/Info"
/dbs_and_roles:
get:
tags:
@@ -508,14 +537,12 @@ components:
properties:
extname:
type: string
version:
type: string
versions:
type: array
items:
type: string
n_databases:
type: integer
owned_by_superuser:
type: integer
SetRoleGrantsRequest:
type: object

View File

@@ -1,20 +0,0 @@
use std::sync::Arc;
use axum::{extract::State, response::Response};
use compute_api::responses::ComputeStatus;
use http::StatusCode;
use crate::{checker::check_writability, compute::ComputeNode, http::JsonResponse};
/// Check that the compute is currently running.
pub(in crate::http) async fn is_writable(State(compute): State<Arc<ComputeNode>>) -> Response {
let status = compute.get_status();
if status != ComputeStatus::Running {
return JsonResponse::invalid_status(status);
}
match check_writability(&compute).await {
Ok(_) => JsonResponse::success(StatusCode::OK, true),
Err(e) => JsonResponse::error(StatusCode::INTERNAL_SERVER_ERROR, e),
}
}

View File

@@ -1,91 +0,0 @@
use std::sync::Arc;
use axum::{extract::State, response::Response};
use compute_api::{
requests::ConfigurationRequest,
responses::{ComputeStatus, ComputeStatusResponse},
};
use http::StatusCode;
use tokio::task;
use tracing::info;
use crate::{
compute::{ComputeNode, ParsedSpec},
http::{extract::Json, JsonResponse},
};
// Accept spec in JSON format and request compute configuration. If anything
// goes wrong after we set the compute status to `ConfigurationPending` and
// update compute state with new spec, we basically leave compute in the
// potentially wrong state. That said, it's control-plane's responsibility to
// watch compute state after reconfiguration request and to clean restart in
// case of errors.
pub(in crate::http) async fn configure(
State(compute): State<Arc<ComputeNode>>,
request: Json<ConfigurationRequest>,
) -> Response {
if !compute.live_config_allowed {
return JsonResponse::error(
StatusCode::PRECONDITION_FAILED,
"live configuration is not allowed for this compute node".to_string(),
);
}
let pspec = match ParsedSpec::try_from(request.spec.clone()) {
Ok(p) => p,
Err(e) => return JsonResponse::error(StatusCode::BAD_REQUEST, e),
};
// XXX: wrap state update under lock in a code block. Otherwise, we will try
// to `Send` `mut state` into the spawned thread bellow, which will cause
// the following rustc error:
//
// error: future cannot be sent between threads safely
{
let mut state = compute.state.lock().unwrap();
if !matches!(state.status, ComputeStatus::Empty | ComputeStatus::Running) {
return JsonResponse::invalid_status(state.status);
}
state.pspec = Some(pspec);
state.set_status(ComputeStatus::ConfigurationPending, &compute.state_changed);
drop(state);
}
// Spawn a blocking thread to wait for compute to become Running. This is
// needed to do not block the main pool of workers and be able to serve
// other requests while some particular request is waiting for compute to
// finish configuration.
let c = compute.clone();
let completed = task::spawn_blocking(move || {
let mut state = c.state.lock().unwrap();
while state.status != ComputeStatus::Running {
state = c.state_changed.wait(state).unwrap();
info!(
"waiting for compute to become {}, current status: {}",
ComputeStatus::Running,
state.status
);
if state.status == ComputeStatus::Failed {
let err = state.error.as_ref().map_or("unknown error", |x| x);
let msg = format!("compute configuration failed: {:?}", err);
return Err(msg);
}
}
Ok(())
})
.await
.unwrap();
if let Err(e) = completed {
return JsonResponse::error(StatusCode::INTERNAL_SERVER_ERROR, e);
}
// Return current compute state if everything went well.
let state = compute.state.lock().unwrap().clone();
let body = ComputeStatusResponse::from(&state);
JsonResponse::success(StatusCode::OK, body)
}

View File

@@ -1,34 +0,0 @@
use std::sync::Arc;
use axum::{body::Body, extract::State, response::Response};
use http::{header::CONTENT_TYPE, StatusCode};
use serde::Deserialize;
use crate::{
catalog::{get_database_schema, SchemaDumpError},
compute::ComputeNode,
http::{extract::Query, JsonResponse},
};
#[derive(Debug, Clone, Deserialize)]
pub(in crate::http) struct DatabaseSchemaParams {
database: String,
}
/// Get a schema dump of the requested database.
pub(in crate::http) async fn get_schema_dump(
params: Query<DatabaseSchemaParams>,
State(compute): State<Arc<ComputeNode>>,
) -> Response {
match get_database_schema(&compute, &params.database).await {
Ok(schema) => Response::builder()
.status(StatusCode::OK)
.header(CONTENT_TYPE.as_str(), "application/json")
.body(Body::from_stream(schema))
.unwrap(),
Err(SchemaDumpError::DatabaseDoesNotExist) => {
JsonResponse::error(StatusCode::NOT_FOUND, SchemaDumpError::DatabaseDoesNotExist)
}
Err(e) => JsonResponse::error(StatusCode::INTERNAL_SERVER_ERROR, e),
}
}

View File

@@ -1,16 +0,0 @@
use std::sync::Arc;
use axum::{extract::State, response::Response};
use http::StatusCode;
use crate::{catalog::get_dbs_and_roles, compute::ComputeNode, http::JsonResponse};
/// Get the databases and roles from the compute.
pub(in crate::http) async fn get_catalog_objects(
State(compute): State<Arc<ComputeNode>>,
) -> Response {
match get_dbs_and_roles(&compute).await {
Ok(catalog_objects) => JsonResponse::success(StatusCode::OK, catalog_objects),
Err(e) => JsonResponse::error(StatusCode::INTERNAL_SERVER_ERROR, e),
}
}

View File

@@ -1,68 +0,0 @@
use std::sync::Arc;
use axum::{
extract::State,
response::{IntoResponse, Response},
};
use http::StatusCode;
use serde::Deserialize;
use crate::{
compute::ComputeNode,
http::{
extract::{Path, Query},
JsonResponse,
},
};
#[derive(Debug, Clone, Deserialize)]
pub(in crate::http) struct ExtensionServerParams {
#[serde(default)]
is_library: bool,
}
/// Download a remote extension.
pub(in crate::http) async fn download_extension(
Path(filename): Path<String>,
params: Query<ExtensionServerParams>,
State(compute): State<Arc<ComputeNode>>,
) -> Response {
// Don't even try to download extensions if no remote storage is configured
if compute.ext_remote_storage.is_none() {
return JsonResponse::error(
StatusCode::PRECONDITION_FAILED,
"remote storage is not configured",
);
}
let ext = {
let state = compute.state.lock().unwrap();
let pspec = state.pspec.as_ref().unwrap();
let spec = &pspec.spec;
let remote_extensions = match spec.remote_extensions.as_ref() {
Some(r) => r,
None => {
return JsonResponse::error(
StatusCode::CONFLICT,
"information about remote extensions is unavailable",
);
}
};
remote_extensions.get_ext(
&filename,
params.is_library,
&compute.build_tag,
&compute.pgversion,
)
};
match ext {
Ok((ext_name, ext_path)) => match compute.download_extension(ext_name, ext_path).await {
Ok(_) => StatusCode::OK.into_response(),
Err(e) => JsonResponse::error(StatusCode::INTERNAL_SERVER_ERROR, e),
},
Err(e) => JsonResponse::error(StatusCode::NOT_FOUND, e),
}
}

View File

@@ -1,45 +0,0 @@
use std::sync::Arc;
use axum::{extract::State, response::Response};
use compute_api::{
requests::ExtensionInstallRequest,
responses::{ComputeStatus, ExtensionInstallResponse},
};
use http::StatusCode;
use crate::{
compute::ComputeNode,
http::{extract::Json, JsonResponse},
};
/// Install a extension.
pub(in crate::http) async fn install_extension(
State(compute): State<Arc<ComputeNode>>,
request: Json<ExtensionInstallRequest>,
) -> Response {
let status = compute.get_status();
if status != ComputeStatus::Running {
return JsonResponse::invalid_status(status);
}
match compute
.install_extension(
&request.extension,
&request.database,
request.version.to_string(),
)
.await
{
Ok(version) => JsonResponse::success(
StatusCode::CREATED,
Some(ExtensionInstallResponse {
extension: request.extension.clone(),
version,
}),
),
Err(e) => JsonResponse::error(
StatusCode::INTERNAL_SERVER_ERROR,
format!("failed to install extension: {e}"),
),
}
}

View File

@@ -1,35 +0,0 @@
use axum::response::{IntoResponse, Response};
use http::StatusCode;
use tracing::info;
use utils::failpoint_support::{apply_failpoint, ConfigureFailpointsRequest};
use crate::http::{extract::Json, JsonResponse};
/// Configure failpoints for testing purposes.
pub(in crate::http) async fn configure_failpoints(
failpoints: Json<ConfigureFailpointsRequest>,
) -> Response {
if !fail::has_failpoints() {
return JsonResponse::error(
StatusCode::PRECONDITION_FAILED,
"Cannot manage failpoints because neon was compiled without failpoints support",
);
}
for fp in &*failpoints {
info!("cfg failpoint: {} {}", fp.name, fp.actions);
// We recognize one extra "action" that's not natively recognized
// by the failpoints crate: exit, to immediately kill the process
let cfg_result = apply_failpoint(&fp.name, &fp.actions);
if let Err(e) = cfg_result {
return JsonResponse::error(
StatusCode::BAD_REQUEST,
format!("failed to configure failpoints: {e}"),
);
}
}
StatusCode::OK.into_response()
}

View File

@@ -1,48 +0,0 @@
use std::sync::Arc;
use axum::{extract::State, response::Response};
use compute_api::{
requests::SetRoleGrantsRequest,
responses::{ComputeStatus, SetRoleGrantsResponse},
};
use http::StatusCode;
use crate::{
compute::ComputeNode,
http::{extract::Json, JsonResponse},
};
/// Add grants for a role.
pub(in crate::http) async fn add_grant(
State(compute): State<Arc<ComputeNode>>,
request: Json<SetRoleGrantsRequest>,
) -> Response {
let status = compute.get_status();
if status != ComputeStatus::Running {
return JsonResponse::invalid_status(status);
}
match compute
.set_role_grants(
&request.database,
&request.schema,
&request.privileges,
&request.role,
)
.await
{
Ok(()) => JsonResponse::success(
StatusCode::CREATED,
Some(SetRoleGrantsResponse {
database: request.database.clone(),
schema: request.schema.clone(),
role: request.role.clone(),
privileges: request.privileges.clone(),
}),
),
Err(e) => JsonResponse::error(
StatusCode::INTERNAL_SERVER_ERROR,
format!("failed to grant role privileges to the schema: {e}"),
),
}
}

View File

@@ -1,18 +0,0 @@
use std::sync::Arc;
use axum::{extract::State, response::Response};
use compute_api::responses::ComputeStatus;
use http::StatusCode;
use crate::{compute::ComputeNode, http::JsonResponse};
/// Collect current Postgres usage insights.
pub(in crate::http) async fn get_insights(State(compute): State<Arc<ComputeNode>>) -> Response {
let status = compute.get_status();
if status != ComputeStatus::Running {
return JsonResponse::invalid_status(status);
}
let insights = compute.collect_insights().await;
JsonResponse::success(StatusCode::OK, insights)
}

View File

@@ -1,31 +0,0 @@
use axum::{body::Body, response::Response};
use http::header::CONTENT_TYPE;
use http::StatusCode;
use metrics::proto::MetricFamily;
use metrics::{Encoder, TextEncoder};
use crate::{http::JsonResponse, metrics::collect};
/// Expose Prometheus metrics.
pub(in crate::http) async fn get_metrics() -> Response {
// When we call TextEncoder::encode() below, it will immediately return an
// error if a metric family has no metrics, so we need to preemptively
// filter out metric families with no metrics.
let metrics = collect()
.into_iter()
.filter(|m| !m.get_metric().is_empty())
.collect::<Vec<MetricFamily>>();
let encoder = TextEncoder::new();
let mut buffer = vec![];
if let Err(e) = encoder.encode(&metrics, &mut buffer) {
return JsonResponse::error(StatusCode::INTERNAL_SERVER_ERROR, e);
}
Response::builder()
.status(StatusCode::OK)
.header(CONTENT_TYPE, encoder.format_type())
.body(Body::from(buffer))
.unwrap()
}

View File

@@ -1,12 +0,0 @@
use std::sync::Arc;
use axum::{extract::State, response::Response};
use http::StatusCode;
use crate::{compute::ComputeNode, http::JsonResponse};
/// Get startup metrics.
pub(in crate::http) async fn get_metrics(State(compute): State<Arc<ComputeNode>>) -> Response {
let metrics = compute.state.lock().unwrap().metrics.clone();
JsonResponse::success(StatusCode::OK, metrics)
}

View File

@@ -1,36 +0,0 @@
use compute_api::responses::ComputeStatusResponse;
use crate::compute::ComputeState;
pub(in crate::http) mod check_writability;
pub(in crate::http) mod configure;
pub(in crate::http) mod database_schema;
pub(in crate::http) mod dbs_and_roles;
pub(in crate::http) mod extension_server;
pub(in crate::http) mod extensions;
pub(in crate::http) mod failpoints;
pub(in crate::http) mod grants;
pub(in crate::http) mod insights;
pub(in crate::http) mod metrics;
pub(in crate::http) mod metrics_json;
pub(in crate::http) mod status;
pub(in crate::http) mod terminate;
impl From<&ComputeState> for ComputeStatusResponse {
fn from(state: &ComputeState) -> Self {
ComputeStatusResponse {
start_time: state.start_time,
tenant: state
.pspec
.as_ref()
.map(|pspec| pspec.tenant_id.to_string()),
timeline: state
.pspec
.as_ref()
.map(|pspec| pspec.timeline_id.to_string()),
status: state.status,
last_active: state.last_active,
error: state.error.clone(),
}
}
}

View File

@@ -1,14 +0,0 @@
use std::{ops::Deref, sync::Arc};
use axum::{extract::State, http::StatusCode, response::Response};
use compute_api::responses::ComputeStatusResponse;
use crate::{compute::ComputeNode, http::JsonResponse};
/// Retrieve the state of the comute.
pub(in crate::http) async fn get_status(State(compute): State<Arc<ComputeNode>>) -> Response {
let state = compute.state.lock().unwrap();
let body = ComputeStatusResponse::from(state.deref());
JsonResponse::success(StatusCode::OK, body)
}

View File

@@ -1,58 +0,0 @@
use std::sync::Arc;
use axum::{
extract::State,
response::{IntoResponse, Response},
};
use compute_api::responses::ComputeStatus;
use http::StatusCode;
use tokio::task;
use tracing::info;
use crate::{
compute::{forward_termination_signal, ComputeNode},
http::JsonResponse,
};
/// Terminate the compute.
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 {
return StatusCode::CREATED.into_response();
}
if !matches!(state.status, ComputeStatus::Empty | ComputeStatus::Running) {
return JsonResponse::invalid_status(state.status);
}
state.set_status(ComputeStatus::TerminationPending, &compute.state_changed);
drop(state);
}
forward_termination_signal();
info!("sent signal and notified waiters");
// Spawn a blocking thread to wait for compute to become Terminated.
// This is needed to do not block the main pool of workers and
// be able to serve other requests while some particular request
// is waiting for compute to finish configuration.
let c = compute.clone();
task::spawn_blocking(move || {
let mut state = c.state.lock().unwrap();
while state.status != ComputeStatus::Terminated {
state = c.state_changed.wait(state).unwrap();
info!(
"waiting for compute to become {}, current status: {:?}",
ComputeStatus::Terminated,
state.status
);
}
})
.await
.unwrap();
info!("terminated Postgres");
StatusCode::OK.into_response()
}

View File

@@ -1,149 +0,0 @@
use std::{
net::{IpAddr, Ipv6Addr, SocketAddr},
sync::Arc,
thread,
time::Duration,
};
use anyhow::Result;
use axum::{
extract::Request,
middleware::{self, Next},
response::{IntoResponse, Response},
routing::{get, post},
Router,
};
use http::StatusCode;
use tokio::net::TcpListener;
use tower::ServiceBuilder;
use tower_http::{request_id::PropagateRequestIdLayer, trace::TraceLayer};
use tracing::{debug, error, info, Span};
use uuid::Uuid;
use super::routes::{
check_writability, configure, database_schema, dbs_and_roles, extension_server, extensions,
grants, insights, metrics, metrics_json, status, terminate,
};
use crate::compute::ComputeNode;
async fn handle_404() -> Response {
StatusCode::NOT_FOUND.into_response()
}
const X_REQUEST_ID: &str = "x-request-id";
/// This middleware function allows compute_ctl to generate its own request ID
/// if one isn't supplied. The control plane will always send one as a UUID. The
/// neon Postgres extension on the other hand does not send one.
async fn maybe_add_request_id_header(mut request: Request, next: Next) -> Response {
let headers = request.headers_mut();
if headers.get(X_REQUEST_ID).is_none() {
headers.append(X_REQUEST_ID, Uuid::new_v4().to_string().parse().unwrap());
}
next.run(request).await
}
/// Run the HTTP server and wait on it forever.
#[tokio::main]
async fn serve(port: u16, compute: Arc<ComputeNode>) {
let mut app = Router::new()
.route("/check_writability", post(check_writability::is_writable))
.route("/configure", post(configure::configure))
.route("/database_schema", get(database_schema::get_schema_dump))
.route("/dbs_and_roles", get(dbs_and_roles::get_catalog_objects))
.route(
"/extension_server/{*filename}",
post(extension_server::download_extension),
)
.route("/extensions", post(extensions::install_extension))
.route("/grants", post(grants::add_grant))
.route("/insights", get(insights::get_insights))
.route("/metrics", get(metrics::get_metrics))
.route("/metrics.json", get(metrics_json::get_metrics))
.route("/status", get(status::get_status))
.route("/terminate", post(terminate::terminate))
.fallback(handle_404)
.layer(
ServiceBuilder::new()
// Add this middleware since we assume the request ID exists
.layer(middleware::from_fn(maybe_add_request_id_header))
.layer(
TraceLayer::new_for_http()
.on_request(|request: &http::Request<_>, _span: &Span| {
let request_id = request
.headers()
.get(X_REQUEST_ID)
.unwrap()
.to_str()
.unwrap();
match request.uri().path() {
"/metrics" => {
debug!(%request_id, "{} {}", request.method(), request.uri())
}
_ => info!(%request_id, "{} {}", request.method(), request.uri()),
};
})
.on_response(
|response: &http::Response<_>, latency: Duration, _span: &Span| {
let request_id = response
.headers()
.get(X_REQUEST_ID)
.unwrap()
.to_str()
.unwrap();
info!(
%request_id,
code = response.status().as_u16(),
latency = latency.as_millis()
)
},
),
)
.layer(PropagateRequestIdLayer::x_request_id()),
)
.with_state(compute);
// Add in any testing support
if cfg!(feature = "testing") {
use super::routes::failpoints;
app = app.route("/failpoints", post(failpoints::configure_failpoints))
}
// This usually binds to both IPv4 and IPv6 on Linux, see
// https://github.com/rust-lang/rust/pull/34440 for more information
let addr = SocketAddr::new(IpAddr::from(Ipv6Addr::UNSPECIFIED), port);
let listener = match TcpListener::bind(&addr).await {
Ok(listener) => listener,
Err(e) => {
error!(
"failed to bind the compute_ctl HTTP server to port {}: {}",
port, e
);
return;
}
};
if let Ok(local_addr) = listener.local_addr() {
info!("compute_ctl HTTP server listening on {}", local_addr);
} else {
info!("compute_ctl HTTP server listening on port {}", port);
}
if let Err(e) = axum::serve(listener, app).await {
error!("compute_ctl HTTP server error: {}", e);
}
}
/// Launch a separate HTTP server thread and return its `JoinHandle`.
pub fn launch_http_server(port: u16, state: &Arc<ComputeNode>) -> Result<thread::JoinHandle<()>> {
let state = Arc::clone(state);
Ok(thread::Builder::new()
.name("http-server".into())
.spawn(move || serve(port, state))?)
}

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