Compare commits

..

20 Commits

Author SHA1 Message Date
Conrad Ludgate
f3f7d0d3f1 zero-copy jwt claim validation 2024-09-30 12:47:07 +01:00
Conrad Ludgate
0724df1d3f stash 2024-09-29 20:29:26 +01:00
Conrad Ludgate
4d47049b00 split up jwt tests 2024-09-27 16:31:49 +01:00
Conrad Ludgate
5687384a8e remove deref impl 2024-09-27 11:43:34 +01:00
Conrad Ludgate
249f5ea17d cleaner local-proxy conn error code 2024-09-27 11:43:34 +01:00
Conrad Ludgate
6abcc1f298 add explicit panic reason 2024-09-27 11:43:34 +01:00
Conrad Ludgate
3e97cf0d6e refine missing credentials error 2024-09-27 11:43:34 +01:00
Conrad Ludgate
054ef4988b update certification comment 2024-09-27 11:43:34 +01:00
Conrad Ludgate
5202cd75b5 only forward expected headers 2024-09-27 11:43:34 +01:00
Conrad Ludgate
f475dac0e6 keepalive while idle 2024-09-27 11:43:34 +01:00
Conrad Ludgate
a4100373e5 fix common name parsing 2024-09-27 11:43:34 +01:00
Conrad Ludgate
040d8cf4f6 fix common name parsing 2024-09-27 11:43:34 +01:00
Conrad Ludgate
75bfd57e01 add authbroker cli flag and fix http2 ka 2024-09-27 11:43:34 +01:00
Conrad Ludgate
4bc2686dee small tweaks 2024-09-27 11:43:34 +01:00
Conrad Ludgate
8e7d2aab76 put it all together 2024-09-27 11:43:34 +01:00
Conrad Ludgate
2703abccc7 start on http2 local proxy connection pool 2024-09-27 11:43:34 +01:00
Conrad Ludgate
76515cdae3 split out auth info from conn info, return the jwt as the auth keys 2024-09-27 11:43:34 +01:00
Conrad Ludgate
08c7f933a3 add support for console backend jwt 2024-09-27 11:43:34 +01:00
Conrad Ludgate
4ad3aa7c96 update doc comment for get_with_url 2024-09-27 10:24:50 +01:00
Conrad Ludgate
9c59e3b4b9 proxy: add jwks endpoint to control plane and mock providers 2024-09-27 10:24:43 +01:00
861 changed files with 22761 additions and 65705 deletions

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

@@ -5,7 +5,9 @@
!Cargo.toml
!Makefile
!rust-toolchain.toml
!scripts/combine_control_files.py
!scripts/ninstall.sh
!vm-cgconfig.conf
!docker-compose/run-tests.sh
# Directories
@@ -15,12 +17,15 @@
!compute_tools/
!control_plane/
!libs/
!neon_local/
!pageserver/
!patches/
!pgxn/
!proxy/
!storage_scrubber/
!safekeeper/
!storage_broker/
!storage_controller/
!trace/
!vendor/postgres-*/
!workspace_hack/

View File

@@ -20,4 +20,3 @@ config-variables:
- REMOTE_STORAGE_AZURE_REGION
- SLACK_UPCOMING_RELEASE_CHANNEL_ID
- DEV_AWS_OIDC_ROLE_ARN
- BENCHMARK_INGEST_TARGET_PROJECTID

View File

@@ -7,10 +7,6 @@ inputs:
type: boolean
required: false
default: false
aws_oicd_role_arn:
description: 'the OIDC role arn to (re-)acquire for allure report upload - if not set call must acquire OIDC role'
required: false
default: ''
outputs:
base-url:
@@ -43,8 +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
@@ -84,14 +79,6 @@ runs:
ALLURE_VERSION: 2.27.0
ALLURE_ZIP_SHA256: b071858fb2fa542c65d8f152c5c40d26267b2dfb74df1f1608a589ecca38e777
- name: (Re-)configure AWS credentials # necessary to upload reports to S3 after a long-running test
if: ${{ !cancelled() && (inputs.aws_oicd_role_arn != '') }}
uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: eu-central-1
role-to-assume: ${{ inputs.aws_oicd_role_arn }}
role-duration-seconds: 3600 # 1 hour should be more than enough to upload report
# Potentially we could have several running build for the same key (for example, for the main branch), so we use improvised lock for this
- name: Acquire lock
shell: bash -euxo pipefail {0}
@@ -196,7 +183,7 @@ runs:
uses: actions/cache@v4
with:
path: ~/.cache/pypoetry/virtualenvs
key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-bookworm-${{ hashFiles('poetry.lock') }}
key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-${{ hashFiles('poetry.lock') }}
- name: Store Allure test stat in the DB (new)
if: ${{ !cancelled() && inputs.store-test-results-into-db == 'true' }}
@@ -234,8 +221,6 @@ runs:
REPORT_URL: ${{ steps.generate-report.outputs.report-url }}
COMMIT_SHA: ${{ github.event.pull_request.head.sha || github.sha }}
with:
# Retry script for 5XX server errors: https://github.com/actions/github-script#retries
retries: 5
script: |
const { REPORT_URL, COMMIT_SHA } = process.env

View File

@@ -8,10 +8,6 @@ inputs:
unique-key:
description: 'string to distinguish different results in the same run'
required: true
aws_oicd_role_arn:
description: 'the OIDC role arn to (re-)acquire for allure report upload - if not set call must acquire OIDC role'
required: false
default: ''
runs:
using: "composite"
@@ -23,8 +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
@@ -36,14 +31,6 @@ runs:
env:
REPORT_DIR: ${{ inputs.report-dir }}
- name: (Re-)configure AWS credentials # necessary to upload reports to S3 after a long-running test
if: ${{ !cancelled() && (inputs.aws_oicd_role_arn != '') }}
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 # 1 hour should be more than enough to upload report
- name: Upload test results
shell: bash -euxo pipefail {0}
run: |

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:
@@ -48,10 +48,6 @@ inputs:
description: 'benchmark durations JSON'
required: false
default: '{}'
aws_oicd_role_arn:
description: 'the OIDC role arn to (re-)acquire for allure report upload - if not set call must acquire OIDC role'
required: false
default: ''
runs:
using: "composite"
@@ -92,7 +88,7 @@ runs:
uses: actions/cache@v4
with:
path: ~/.cache/pypoetry/virtualenvs
key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-bookworm-${{ hashFiles('poetry.lock') }}
key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-${{ hashFiles('poetry.lock') }}
- name: Install Python deps
shell: bash -euxo pipefail {0}
@@ -108,7 +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: |
@@ -154,8 +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 $EXTRA_PARAMS"
fi
# We use pytest-split plugin to run benchmarks in parallel on different CI runners
@@ -215,17 +218,7 @@ runs:
name: compatibility-snapshot-${{ runner.arch }}-${{ inputs.build_type }}-pg${{ inputs.pg_version }}
# Directory is created by test_compatibility.py::test_create_snapshot, keep the path in sync with the test
path: /tmp/test_output/compatibility_snapshot_pg${{ inputs.pg_version }}/
# 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
- name: (Re-)configure AWS credentials # necessary to upload reports to S3 after a long-running test
if: ${{ !cancelled() && (inputs.aws_oicd_role_arn != '') }}
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 # 1 hour should be more than enough to upload report
- name: Upload test results
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-store

View File

@@ -0,0 +1,36 @@
name: "Set custom docker config directory"
description: "Create a directory for docker config and set DOCKER_CONFIG"
# Use custom DOCKER_CONFIG directory to avoid conflicts with default settings
runs:
using: "composite"
steps:
- name: Show warning on GitHub-hosted runners
if: runner.environment == 'github-hosted'
shell: bash -euo pipefail {0}
run: |
# Using the following environment variables to find a path to the workflow file
# ${GITHUB_WORKFLOW_REF} - octocat/hello-world/.github/workflows/my-workflow.yml@refs/heads/my_branch
# ${GITHUB_REPOSITORY} - octocat/hello-world
# ${GITHUB_REF} - refs/heads/my_branch
# From https://docs.github.com/en/actions/writing-workflows/choosing-what-your-workflow-does/variables
filename_with_ref=${GITHUB_WORKFLOW_REF#"$GITHUB_REPOSITORY/"}
filename=${filename_with_ref%"@$GITHUB_REF"}
# https://docs.github.com/en/actions/writing-workflows/choosing-what-your-workflow-does/workflow-commands-for-github-actions#setting-a-warning-message
title='Unnecessary usage of `.github/actions/set-docker-config-dir`'
message='No need to use `.github/actions/set-docker-config-dir` action on GitHub-hosted runners'
echo "::warning file=${filename},title=${title}::${message}"
- uses: pyTooling/Actions/with-post-step@74afc5a42a17a046c90c68cb5cfa627e5c6c5b6b # v1.0.7
env:
DOCKER_CONFIG: .docker-custom-${{ github.run_id }}-${{ github.run_attempt }}
with:
main: |
mkdir -p "${DOCKER_CONFIG}"
echo DOCKER_CONFIG=${DOCKER_CONFIG} | tee -a $GITHUB_ENV
post: |
if [ -d "${DOCKER_CONFIG}" ]; then
rm -r "${DOCKER_CONFIG}"
fi

View File

@@ -7,10 +7,6 @@ inputs:
path:
description: "A directory or file to upload"
required: true
skip-if-does-not-exist:
description: "Allow to skip if path doesn't exist, fail otherwise"
default: false
required: false
prefix:
description: "S3 prefix. Default is '${GITHUB_SHA}/${GITHUB_RUN_ID}/${GITHUB_RUN_ATTEMPT}'"
required: false
@@ -19,12 +15,10 @@ runs:
using: "composite"
steps:
- name: Prepare artifact
id: prepare-artifact
shell: bash -euxo pipefail {0}
env:
SOURCE: ${{ inputs.path }}
ARCHIVE: /tmp/uploads/${{ inputs.name }}.tar.zst
SKIP_IF_DOES_NOT_EXIST: ${{ inputs.skip-if-does-not-exist }}
run: |
mkdir -p $(dirname $ARCHIVE)
@@ -39,22 +33,14 @@ runs:
elif [ -f ${SOURCE} ]; then
time tar -cf ${ARCHIVE} --zstd ${SOURCE}
elif ! ls ${SOURCE} > /dev/null 2>&1; then
if [ "${SKIP_IF_DOES_NOT_EXIST}" = "true" ]; then
echo 'SKIPPED=true' >> $GITHUB_OUTPUT
exit 0
else
echo >&2 "${SOURCE} does not exist"
exit 2
fi
echo >&2 "${SOURCE} does not exist"
exit 2
else
echo >&2 "${SOURCE} is neither a directory nor a file, do not know how to handle it"
exit 3
fi
echo 'SKIPPED=false' >> $GITHUB_OUTPUT
- name: Upload artifact
if: ${{ steps.prepare-artifact.outputs.SKIPPED == 'false' }}
shell: bash -euxo pipefail {0}
env:
SOURCE: ${{ inputs.path }}

View File

@@ -1,3 +1,14 @@
## Problem
## Summary of changes
## Checklist before requesting a review
- [ ] I have performed a self-review of my code.
- [ ] If it is a core feature, I have added thorough tests.
- [ ] Do we need to implement analytics? if so did you add the relevant metrics to the dashboard?
- [ ] If this PR requires public announcement, mark it with /release-notes label and add several sentences in this section.
## Checklist before merging
- [ ] Do not forget to reformat commit message to not include the above checklist

View File

@@ -3,23 +3,19 @@ name: Prepare benchmarking databases by restoring dumps
on:
workflow_call:
# no inputs needed
defaults:
run:
shell: bash -euxo pipefail {0}
jobs:
setup-databases:
permissions:
contents: write
statuses: write
id-token: write # aws-actions/configure-aws-credentials
strategy:
fail-fast: false
matrix:
platform: [ aws-rds-postgres, aws-aurora-serverless-v2-postgres, neon ]
platform: [ aws-rds-postgres, aws-aurora-serverless-v2-postgres, neon ]
database: [ clickbench, tpch, userexample ]
env:
LD_LIBRARY_PATH: /tmp/neon/pg_install/v16/lib
PLATFORM: ${{ matrix.platform }}
@@ -27,10 +23,7 @@ jobs:
runs-on: [ self-hosted, us-east-2, x64 ]
container:
image: neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/build-tools:pinned
options: --init
steps:
@@ -39,13 +32,13 @@ jobs:
run: |
case "${PLATFORM}" in
neon)
CONNSTR=${{ secrets.BENCHMARK_CAPTEST_CONNSTR }}
CONNSTR=${{ secrets.BENCHMARK_CAPTEST_CONNSTR }}
;;
aws-rds-postgres)
CONNSTR=${{ secrets.BENCHMARK_RDS_POSTGRES_CONNSTR }}
CONNSTR=${{ secrets.BENCHMARK_RDS_POSTGRES_CONNSTR }}
;;
aws-aurora-serverless-v2-postgres)
CONNSTR=${{ secrets.BENCHMARK_RDS_AURORA_CONNSTR }}
CONNSTR=${{ secrets.BENCHMARK_RDS_AURORA_CONNSTR }}
;;
*)
echo >&2 "Unknown PLATFORM=${PLATFORM}"
@@ -53,17 +46,10 @@ jobs:
;;
esac
echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
- 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
- name: Download Neon artifact
uses: ./.github/actions/download
with:
@@ -71,23 +57,23 @@ jobs:
path: /tmp/neon/
prefix: latest
# we create a table that has one row for each database that we want to restore with the status whether the restore is done
# 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
env:
BENCHMARK_CONNSTR: ${{ steps.set-up-prep-connstr.outputs.connstr }}
DATABASE_NAME: ${{ matrix.database }}
# to avoid a race condition of multiple jobs trying to create the table at the same time,
# to avoid a race condition of multiple jobs trying to create the table at the same time,
# we use an advisory lock
run: |
${PG_BINARIES}/psql "${{ env.BENCHMARK_CONNSTR }}" -c "
SELECT pg_advisory_lock(4711);
SELECT pg_advisory_lock(4711);
CREATE TABLE IF NOT EXISTS benchmark_restore_status (
databasename text primary key,
restore_done boolean
);
SELECT pg_advisory_unlock(4711);
"
- name: Check if restore is already done
id: check-restore-done
env:
@@ -121,7 +107,7 @@ jobs:
DATABASE_NAME: ${{ matrix.database }}
run: |
mkdir -p /tmp/dumps
aws s3 cp s3://neon-github-dev/performance/pgdumps/$DATABASE_NAME/$DATABASE_NAME.pg_dump /tmp/dumps/
aws s3 cp s3://neon-github-dev/performance/pgdumps/$DATABASE_NAME/$DATABASE_NAME.pg_dump /tmp/dumps/
- name: Replace database name in connection string
if: steps.check-restore-done.outputs.skip != 'true'
@@ -140,17 +126,17 @@ jobs:
else
new_connstr="${base_connstr}/${DATABASE_NAME}"
fi
echo "database_connstr=${new_connstr}" >> $GITHUB_OUTPUT
echo "database_connstr=${new_connstr}" >> $GITHUB_OUTPUT
- name: Restore dump
if: steps.check-restore-done.outputs.skip != 'true'
env:
DATABASE_NAME: ${{ matrix.database }}
DATABASE_CONNSTR: ${{ steps.replace-dbname.outputs.database_connstr }}
# the following works only with larger computes:
# the following works only with larger computes:
# PGOPTIONS: "-c maintenance_work_mem=8388608 -c max_parallel_maintenance_workers=7"
# we add the || true because:
# the dumps were created with Neon and contain neon extensions that are not
# the dumps were created with Neon and contain neon extensions that are not
# available in RDS, so we will always report an error, but we can ignore it
run: |
${PG_BINARIES}/pg_restore --clean --if-exists --no-owner --jobs=4 \

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 states to run regression tests on'
pg-versions:
description: 'a json array of postgres versions to run regression tests on'
required: true
type: string
@@ -53,6 +53,20 @@ jobs:
BUILD_TAG: ${{ inputs.build-tag }}
steps:
- name: Fix git ownership
run: |
# Workaround for `fatal: detected dubious ownership in repository at ...`
#
# Use both ${{ github.workspace }} and ${GITHUB_WORKSPACE} because they're different on host and in containers
# Ref https://github.com/actions/checkout/issues/785
#
git config --global --add safe.directory ${{ github.workspace }}
git config --global --add safe.directory ${GITHUB_WORKSPACE}
for r in 14 15 16 17; do
git config --global --add safe.directory "${{ github.workspace }}/vendor/postgres-v$r"
git config --global --add safe.directory "${GITHUB_WORKSPACE}/vendor/postgres-v$r"
done
- uses: actions/checkout@v4
with:
submodules: true
@@ -110,28 +124,28 @@ jobs:
uses: actions/cache@v4
with:
path: pg_install/v14
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v14_rev.outputs.pg_rev }}-bookworm-${{ hashFiles('Makefile', 'build-tools.Dockerfile') }}
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v14_rev.outputs.pg_rev }}-${{ hashFiles('Makefile', 'Dockerfile.build-tools') }}
- name: Cache postgres v15 build
id: cache_pg_15
uses: actions/cache@v4
with:
path: pg_install/v15
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v15_rev.outputs.pg_rev }}-bookworm-${{ hashFiles('Makefile', 'build-tools.Dockerfile') }}
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v15_rev.outputs.pg_rev }}-${{ hashFiles('Makefile', 'Dockerfile.build-tools') }}
- name: Cache postgres v16 build
id: cache_pg_16
uses: actions/cache@v4
with:
path: pg_install/v16
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v16_rev.outputs.pg_rev }}-bookworm-${{ hashFiles('Makefile', 'build-tools.Dockerfile') }}
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v16_rev.outputs.pg_rev }}-${{ hashFiles('Makefile', 'Dockerfile.build-tools') }}
- name: Cache postgres v17 build
id: cache_pg_17
uses: actions/cache@v4
with:
path: pg_install/v17
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v17_rev.outputs.pg_rev }}-bookworm-${{ hashFiles('Makefile', 'build-tools.Dockerfile') }}
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v17_rev.outputs.pg_rev }}-${{ hashFiles('Makefile', 'Dockerfile.build-tools') }}
- name: Build postgres v14
if: steps.cache_pg_14.outputs.cache-hit != 'true'
@@ -222,7 +236,9 @@ jobs:
# run pageserver tests with different settings
for io_engine in std-fs tokio-epoll-uring ; do
NEON_PAGESERVER_UNIT_TEST_VIRTUAL_FILE_IOENGINE=$io_engine ${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_FEATURES -E 'package(pageserver)'
for io_buffer_alignment in 0 1 512 ; do
NEON_PAGESERVER_UNIT_TEST_VIRTUAL_FILE_IOENGINE=$io_engine NEON_PAGESERVER_UNIT_TEST_IO_BUFFER_ALIGNMENT=$io_buffer_alignment ${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_FEATURES -E 'package(pageserver)'
done
done
# Run separate tests for real S3
@@ -276,14 +292,14 @@ 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' }}
uses: ./.github/actions/run-python-test-set
timeout-minutes: 60
with:
@@ -293,14 +309,13 @@ 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 }}
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
USE_LFC: ${{ matrix.lfc_state == 'with-lfc' && 'true' || 'false' }}
# Temporary disable this step until we figure out why it's so flaky
# Ref https://github.com/neondatabase/neon/issues/4540

View File

@@ -1,37 +0,0 @@
name: Check Codestyle Python
on:
workflow_call:
inputs:
build-tools-image:
description: 'build-tools image'
required: true
type: string
defaults:
run:
shell: bash -euxo pipefail {0}
jobs:
check-codestyle-python:
runs-on: [ self-hosted, small ]
container:
image: ${{ inputs.build-tools-image }}
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
options: --init
steps:
- uses: actions/checkout@v4
- uses: actions/cache@v4
with:
path: ~/.cache/pypoetry/virtualenvs
key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-bookworm-${{ hashFiles('poetry.lock') }}
- run: ./scripts/pysync
- run: poetry run ruff check .
- run: poetry run ruff format --check .
- run: poetry run mypy .

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

@@ -12,6 +12,7 @@ on:
# │ │ │ ┌───────────── month (1 - 12 or JAN-DEC)
# │ │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
- cron: '0 3 * * *' # run once a day, timezone is utc
workflow_dispatch: # adds ability to run this manually
inputs:
region_id:
@@ -58,7 +59,7 @@ jobs:
permissions:
contents: write
statuses: write
id-token: write # aws-actions/configure-aws-credentials
id-token: write # Required for OIDC authentication in azure runners
strategy:
fail-fast: false
matrix:
@@ -67,10 +68,12 @@ jobs:
PLATFORM: "neon-staging"
region_id: ${{ github.event.inputs.region_id || 'aws-us-east-2' }}
RUNNER: [ self-hosted, us-east-2, x64 ]
IMAGE: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/build-tools:pinned
- DEFAULT_PG_VERSION: 16
PLATFORM: "azure-staging"
region_id: 'azure-eastus2'
RUNNER: [ self-hosted, eastus2, x64 ]
IMAGE: neondatabase/build-tools:pinned
env:
TEST_PG_BENCH_DURATIONS_MATRIX: "300"
TEST_PG_BENCH_SCALES_MATRIX: "10,100"
@@ -83,10 +86,7 @@ jobs:
runs-on: ${{ matrix.RUNNER }}
container:
image: neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
image: ${{ matrix.IMAGE }}
options: --init
steps:
@@ -122,7 +122,6 @@ jobs:
run_in_parallel: false
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
pg_version: ${{ env.DEFAULT_PG_VERSION }}
aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
# 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
@@ -134,7 +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 }}"
@@ -151,14 +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>
@@ -168,10 +164,6 @@ jobs:
replication-tests:
if: ${{ github.event.inputs.run_only_pgvector_tests == 'false' || github.event.inputs.run_only_pgvector_tests == null }}
permissions:
contents: write
statuses: write
id-token: write # aws-actions/configure-aws-credentials
env:
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
DEFAULT_PG_VERSION: 16
@@ -182,21 +174,12 @@ jobs:
runs-on: [ self-hosted, us-east-2, x64 ]
container:
image: neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/build-tools:pinned
options: --init
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
- name: Download Neon artifact
uses: ./.github/actions/download
@@ -214,7 +197,6 @@ 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 }}"
@@ -231,7 +213,6 @@ 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 }}"
@@ -243,13 +224,11 @@ 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: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@v1
with:
channel-id: "C06T9AMNDQQ" # on-call-compute-staging-stream
@@ -288,7 +267,7 @@ jobs:
region_id_default=${{ env.DEFAULT_REGION_ID }}
runner_default='["self-hosted", "us-east-2", "x64"]'
runner_azure='["self-hosted", "eastus2", "x64"]'
image_default="neondatabase/build-tools:pinned-bookworm"
image_default="369495373322.dkr.ecr.eu-central-1.amazonaws.com/build-tools:pinned"
matrix='{
"pg_version" : [
16
@@ -307,9 +286,9 @@ jobs:
"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": "'"$region_id_default"'", "platform": "neonvm-captest-new", "db_size": "50gb","runner": '"$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": "azure-eastus2", "platform": "neonvm-azure-captest-freetier", "db_size": "3gb" ,"runner": '"$runner_azure"', "image": "neondatabase/build-tools:pinned" },
{ "pg_version": 16, "region_id": "azure-eastus2", "platform": "neonvm-azure-captest-new", "db_size": "10gb","runner": '"$runner_azure"', "image": "neondatabase/build-tools:pinned" },
{ "pg_version": 16, "region_id": "azure-eastus2", "platform": "neonvm-azure-captest-new", "db_size": "50gb","runner": '"$runner_azure"', "image": "neondatabase/build-tools:pinned" },
{ "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-sharding-reuse", "db_size": "50gb","runner": '"$runner_default"', "image": "'"$image_default"'" }]
}'
@@ -365,7 +344,7 @@ jobs:
permissions:
contents: write
statuses: write
id-token: write # aws-actions/configure-aws-credentials
id-token: write # Required for OIDC authentication in azure runners
strategy:
fail-fast: false
@@ -392,7 +371,7 @@ jobs:
steps:
- uses: actions/checkout@v4
- name: Configure AWS credentials
- name: Configure AWS credentials # necessary on Azure runners
uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: eu-central-1
@@ -452,7 +431,6 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_init
pg_version: ${{ env.DEFAULT_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 }}"
@@ -467,7 +445,6 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_simple_update
pg_version: ${{ env.DEFAULT_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 }}"
@@ -482,7 +459,6 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_select_only
pg_version: ${{ env.DEFAULT_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 }}"
@@ -499,14 +475,12 @@ 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>
@@ -518,15 +492,17 @@ jobs:
permissions:
contents: write
statuses: write
id-token: write # aws-actions/configure-aws-credentials
id-token: write # Required for OIDC authentication in azure runners
strategy:
fail-fast: false
matrix:
include:
- PLATFORM: "neonvm-captest-pgvector"
RUNNER: [ self-hosted, us-east-2, x64 ]
IMAGE: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/build-tools:pinned
- PLATFORM: "azure-captest-pgvector"
RUNNER: [ self-hosted, eastus2, x64 ]
IMAGE: neondatabase/build-tools:pinned
env:
TEST_PG_BENCH_DURATIONS_MATRIX: "15m"
@@ -535,16 +511,13 @@ jobs:
DEFAULT_PG_VERSION: 16
TEST_OUTPUT: /tmp/test_output
BUILD_TYPE: remote
LD_LIBRARY_PATH: /home/nonroot/pg/usr/lib/x86_64-linux-gnu
SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref_name == 'main' ) }}
PLATFORM: ${{ matrix.PLATFORM }}
runs-on: ${{ matrix.RUNNER }}
container:
image: neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
image: ${{ matrix.IMAGE }}
options: --init
steps:
@@ -554,26 +527,17 @@ jobs:
# instead of using Neon artifacts containing pgbench
- name: Install postgresql-16 where pytest expects it
run: |
# Just to make it easier to test things locally on macOS (with arm64)
arch=$(uname -m | sed 's/x86_64/amd64/g' | sed 's/aarch64/arm64/g')
cd /home/nonroot
wget -q "https://apt.postgresql.org/pub/repos/apt/pool/main/p/postgresql-17/libpq5_17.2-1.pgdg120+1_${arch}.deb"
wget -q "https://apt.postgresql.org/pub/repos/apt/pool/main/p/postgresql-16/postgresql-client-16_16.6-1.pgdg120+1_${arch}.deb"
wget -q "https://apt.postgresql.org/pub/repos/apt/pool/main/p/postgresql-16/postgresql-16_16.6-1.pgdg120+1_${arch}.deb"
dpkg -x libpq5_17.2-1.pgdg120+1_${arch}.deb pg
dpkg -x postgresql-16_16.6-1.pgdg120+1_${arch}.deb pg
dpkg -x postgresql-client-16_16.6-1.pgdg120+1_${arch}.deb pg
wget -q https://apt.postgresql.org/pub/repos/apt/pool/main/p/postgresql-16/libpq5_16.4-1.pgdg110%2B1_amd64.deb
wget -q https://apt.postgresql.org/pub/repos/apt/pool/main/p/postgresql-16/postgresql-client-16_16.4-1.pgdg110%2B1_amd64.deb
wget -q https://apt.postgresql.org/pub/repos/apt/pool/main/p/postgresql-16/postgresql-16_16.4-1.pgdg110%2B1_amd64.deb
dpkg -x libpq5_16.4-1.pgdg110+1_amd64.deb pg
dpkg -x postgresql-client-16_16.4-1.pgdg110+1_amd64.deb pg
dpkg -x postgresql-16_16.4-1.pgdg110+1_amd64.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}" >> ${GITHUB_ENV}
ln -s /home/nonroot/pg/usr/lib/postgresql/16/bin/pgbench /tmp/neon/pg_install/v16/bin/pgbench
ln -s /home/nonroot/pg/usr/lib/postgresql/16/bin/psql /tmp/neon/pg_install/v16/bin/psql
ln -s /home/nonroot/pg/usr/lib/x86_64-linux-gnu /tmp/neon/pg_install/v16/lib
/tmp/neon/pg_install/v16/bin/pgbench --version
/tmp/neon/pg_install/v16/bin/psql --version
@@ -595,7 +559,7 @@ jobs:
echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
- name: Configure AWS credentials
- name: Configure AWS credentials # necessary on Azure runners to read/write from/to S3
uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: eu-central-1
@@ -611,7 +575,6 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_pgvector_indexing
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 }}"
@@ -626,7 +589,6 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600
pg_version: ${{ env.DEFAULT_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 }}"
@@ -636,14 +598,12 @@ 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>
@@ -660,10 +620,6 @@ jobs:
# *_CLICKBENCH_CONNSTR: Genuine ClickBench DB with ~100M rows
# *_CLICKBENCH_10M_CONNSTR: DB with the first 10M rows of ClickBench DB
if: ${{ !cancelled() && (github.event.inputs.run_only_pgvector_tests == 'false' || github.event.inputs.run_only_pgvector_tests == null) }}
permissions:
contents: write
statuses: write
id-token: write # aws-actions/configure-aws-credentials
needs: [ generate-matrices, pgbench-compare, prepare_AWS_RDS_databases ]
strategy:
@@ -682,26 +638,12 @@ jobs:
runs-on: [ self-hosted, us-east-2, x64 ]
container:
image: neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/build-tools:pinned
options: --init
# Increase timeout to 12h, default timeout is 6h
# we have regression in clickbench causing it to run 2-3x longer
timeout-minutes: 720
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
- name: Download Neon artifact
uses: ./.github/actions/download
with:
@@ -737,9 +679,8 @@ jobs:
test_selection: performance/test_perf_olap.py
run_in_parallel: false
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 43200 -k test_clickbench
extra_params: -m remote_cluster --timeout 21600 -k test_clickbench
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 }}"
@@ -752,14 +693,12 @@ 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>
@@ -775,10 +714,6 @@ jobs:
#
# *_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) }}
permissions:
contents: write
statuses: write
id-token: write # aws-actions/configure-aws-credentials
needs: [ generate-matrices, clickbench-compare, prepare_AWS_RDS_databases ]
strategy:
@@ -796,22 +731,12 @@ jobs:
runs-on: [ self-hosted, us-east-2, x64 ]
container:
image: neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/build-tools:pinned
options: --init
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
- name: Download Neon artifact
uses: ./.github/actions/download
with:
@@ -856,7 +781,6 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_tpch
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 }}"
@@ -867,14 +791,12 @@ 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>
@@ -884,10 +806,6 @@ jobs:
user-examples-compare:
if: ${{ !cancelled() && (github.event.inputs.run_only_pgvector_tests == 'false' || github.event.inputs.run_only_pgvector_tests == null) }}
permissions:
contents: write
statuses: write
id-token: write # aws-actions/configure-aws-credentials
needs: [ generate-matrices, tpch-compare, prepare_AWS_RDS_databases ]
strategy:
@@ -904,22 +822,12 @@ jobs:
runs-on: [ self-hosted, us-east-2, x64 ]
container:
image: neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/build-tools:pinned
options: --init
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
- name: Download Neon artifact
uses: ./.github/actions/download
with:
@@ -957,7 +865,6 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_user_examples
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 }}"
@@ -967,14 +874,12 @@ 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

@@ -3,86 +3,32 @@ 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:${{ inputs.image-tag }}
defaults:
run:
shell: bash -euo pipefail {0}
# The initial idea was to prevent the waste of resources by not re-building the `build-tools` image
# for the same tag in parallel workflow runs, and queue them to be skipped once we have
# the first image pushed to Docker registry, but GitHub's concurrency mechanism is not working as expected.
# GitHub can't have more than 1 job in a queue and removes the previous one, it causes failures if the dependent jobs.
#
# Ref https://github.com/orgs/community/discussions/41518
#
# concurrency:
# group: build-build-tools-image-${{ inputs.image-tag }}
# cancel-in-progress: false
concurrency:
group: build-build-tools-image-${{ inputs.image-tag }}
cancel-in-progress: false
# No permission for GITHUB_TOKEN by default; the **minimal required** set of permissions should be granted in each job.
permissions: {}
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 ]
@@ -90,15 +36,27 @@ jobs:
strategy:
matrix:
arch: ${{ fromJson(needs.check-image.outputs.archs) }}
debian: ${{ fromJson(needs.check-image.outputs.debians) }}
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' (${CHECK_IMAGE_TAG})"
exit 1
fi
- uses: actions/checkout@v4
- uses: neondatabase/dev-actions/set-docker-config-dir@6094485bf440001c94a94a3f9e221e81ff6b6193
- uses: ./.github/actions/set-docker-config-dir
- uses: docker/setup-buildx-action@v3
with:
cache-binary: false
@@ -116,22 +74,22 @@ jobs:
- uses: docker/build-push-action@v6
with:
file: build-tools.Dockerfile
context: .
provenance: false
push: true
pull: true
build-args: |
DEBIAN_VERSION=${{ matrix.debian }}
cache-from: type=registry,ref=cache.neon.build/build-tools:cache-${{ matrix.debian }}-${{ matrix.arch }}
cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/build-tools:cache-{0}-{1},mode=max', matrix.debian, matrix.arch) || '' }}
tags: |
neondatabase/build-tools:${{ needs.check-image.outputs.tag }}-${{ matrix.debian }}-${{ matrix.arch }}
file: Dockerfile.build-tools
cache-from: type=registry,ref=cache.neon.build/build-tools:cache-${{ matrix.arch }}
cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/build-tools:cache-{0},mode=max', matrix.arch) || '' }}
tags: neondatabase/build-tools:${{ inputs.image-tag }}-${{ matrix.arch }}
merge-images:
needs: [ check-image, build-image ]
needs: [ build-image ]
runs-on: ubuntu-22.04
env:
IMAGE_TAG: ${{ inputs.image-tag }}
steps:
- uses: docker/login-action@v3
with:
@@ -139,23 +97,7 @@ jobs:
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
- 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 }}
run: |
for debian in ${DEBIANS}; do
tags=("-t" "neondatabase/build-tools:${IMAGE_TAG}-${debian}")
if [ "${EVERYTHING}" == "true" ] && [ "${debian}" == "${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 "${tags[@]}"
done
docker buildx imagetools create -t neondatabase/build-tools:${IMAGE_TAG} \
neondatabase/build-tools:${IMAGE_TAG}-x64 \
neondatabase/build-tools:${IMAGE_TAG}-arm64

View File

@@ -6,7 +6,6 @@ on:
- main
- release
- release-proxy
- release-compute
pull_request:
defaults:
@@ -71,28 +70,25 @@ 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:
needs: [ check-permissions, build-build-tools-image ]
uses: ./.github/workflows/_check-codestyle-python.yml
with:
build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
secrets: inherit
check-codestyle-jsonnet:
needs: [ check-permissions, build-build-tools-image ]
runs-on: [ self-hosted, small ]
container:
@@ -106,14 +102,27 @@ jobs:
- name: Checkout
uses: actions/checkout@v4
- name: Check Jsonnet code formatting
run: |
make -C compute jsonnetfmt-test
- name: Cache poetry deps
uses: actions/cache@v4
with:
path: ~/.cache/pypoetry/virtualenvs
key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-${{ hashFiles('poetry.lock') }}
- name: Install Python deps
run: ./scripts/pysync
- name: Run `ruff check` to ensure code format
run: poetry run ruff check .
- name: Run `ruff format` to ensure code format
run: poetry run ruff format --check .
- name: Run mypy to check types
run: poetry run mypy .
# Check that the vendor/postgres-* submodules point to the
# corresponding REL_*_STABLE_neon branches.
check-submodules:
needs: [ check-permissions ]
runs-on: ubuntu-22.04
steps:
- name: Checkout
@@ -172,7 +181,7 @@ jobs:
runs-on: ${{ fromJson(format('["self-hosted", "{0}"]', matrix.arch == 'arm64' && 'small-arm64' || 'small')) }}
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
image: ${{ needs.build-build-tools-image.outputs.image }}
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
@@ -184,15 +193,16 @@ jobs:
with:
submodules: true
- name: Cache cargo deps
uses: actions/cache@v4
with:
path: |
~/.cargo/registry
!~/.cargo/registry/src
~/.cargo/git
target
key: v1-${{ runner.os }}-${{ runner.arch }}-cargo-${{ hashFiles('./Cargo.lock') }}-${{ hashFiles('./rust-toolchain.toml') }}-rust
# Disabled for now
# - name: Restore cargo deps cache
# id: cache_cargo
# uses: actions/cache@v4
# with:
# path: |
# !~/.cargo/registry/src
# ~/.cargo/git/
# target/
# key: v1-${{ runner.os }}-${{ runner.arch }}-cargo-clippy-${{ hashFiles('rust-toolchain.toml') }}-${{ hashFiles('Cargo.lock') }}
# Some of our rust modules use FFI and need those to be checked
- name: Get postgres headers
@@ -252,18 +262,11 @@ jobs:
uses: ./.github/workflows/_build-and-test-locally.yml
with:
arch: ${{ matrix.arch }}
build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}
build-tag: ${{ needs.tag.outputs.build-tag }}
build-type: ${{ matrix.build-type }}
# Run tests on all Postgres versions in release builds and only on the latest version in debug builds
# run without LFC on v17 release only
test-cfg: |
${{ matrix.build-type == 'release' && '[{"pg_version":"v14", "lfc_state": "without-lfc"},
{"pg_version":"v15", "lfc_state": "without-lfc"},
{"pg_version":"v16", "lfc_state": "without-lfc"},
{"pg_version":"v17", "lfc_state": "without-lfc"},
{"pg_version":"v17", "lfc_state": "with-lfc"}]'
|| '[{"pg_version":"v17", "lfc_state": "without-lfc"}]' }}
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
@@ -274,7 +277,7 @@ jobs:
needs: [ check-permissions, build-build-tools-image ]
runs-on: [ self-hosted, small ]
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
image: ${{ needs.build-build-tools-image.outputs.image }}
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
@@ -287,7 +290,7 @@ jobs:
uses: actions/cache@v4
with:
path: ~/.cache/pypoetry/virtualenvs
key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-bookworm-${{ hashFiles('poetry.lock') }}
key: v1-${{ runner.os }}-${{ runner.arch }}-python-deps-${{ hashFiles('poetry.lock') }}
- name: Install Python deps
run: ./scripts/pysync
@@ -307,7 +310,7 @@ jobs:
needs: [ check-permissions, build-and-test-locally, build-build-tools-image, get-benchmarks-durations ]
runs-on: [ self-hosted, small ]
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
image: ${{ needs.build-build-tools-image.outputs.image }}
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
@@ -338,7 +341,7 @@ jobs:
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
TEST_RESULT_CONNSTR: "${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}"
PAGESERVER_VIRTUAL_FILE_IO_ENGINE: tokio-epoll-uring
SYNC_BETWEEN_TESTS: true
SYNC_AFTER_EACH_TEST: true
# XXX: no coverage data handling here, since benchmarks are run on release builds,
# while coverage is currently collected for the debug ones
@@ -365,7 +368,7 @@ jobs:
runs-on: [ self-hosted, small ]
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
image: ${{ needs.build-build-tools-image.outputs.image }}
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
@@ -413,7 +416,7 @@ jobs:
needs: [ check-permissions, build-build-tools-image, build-and-test-locally ]
runs-on: [ self-hosted, small ]
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
image: ${{ needs.build-build-tools-image.outputs.image }}
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
@@ -501,8 +504,6 @@ jobs:
REPORT_URL_NEW: ${{ steps.upload-coverage-report-new.outputs.report-url }}
COMMIT_SHA: ${{ github.event.pull_request.head.sha || github.sha }}
with:
# Retry script for 5XX server errors: https://github.com/actions/github-script#retries
retries: 5
script: |
const { REPORT_URL_NEW, COMMIT_SHA } = process.env
@@ -516,7 +517,7 @@ 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' }}
if: ${{ !github.event.pull_request.draft || contains( github.event.pull_request.labels.*.name, 'run-e2e-tests-in-draft') || github.ref_name == 'main' || github.ref_name == 'release' || github.ref_name == 'release-proxy' }}
needs: [ check-permissions, promote-images, tag ]
uses: ./.github/workflows/trigger-e2e-tests.yml
secrets: inherit
@@ -534,7 +535,7 @@ jobs:
with:
submodules: true
- uses: neondatabase/dev-actions/set-docker-config-dir@6094485bf440001c94a94a3f9e221e81ff6b6193
- uses: ./.github/actions/set-docker-config-dir
- uses: docker/setup-buildx-action@v3
with:
cache-binary: false
@@ -559,16 +560,15 @@ jobs:
ADDITIONAL_RUSTFLAGS=${{ matrix.arch == 'arm64' && '-Ctarget-feature=+lse -Ctarget-cpu=neoverse-n1' || '' }}
GIT_VERSION=${{ github.event.pull_request.head.sha || github.sha }}
BUILD_TAG=${{ needs.tag.outputs.build-tag }}
TAG=${{ needs.build-build-tools-image.outputs.image-tag }}-bookworm
DEBIAN_VERSION=bookworm
TAG=${{ needs.build-build-tools-image.outputs.image-tag }}
provenance: false
push: true
pull: true
file: Dockerfile
cache-from: type=registry,ref=cache.neon.build/neon:cache-bookworm-${{ matrix.arch }}
cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/neon:cache-{0}-{1},mode=max', 'bookworm', matrix.arch) || '' }}
cache-from: type=registry,ref=cache.neon.build/neon:cache-${{ matrix.arch }}
cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/neon:cache-{0},mode=max', matrix.arch) || '' }}
tags: |
neondatabase/neon:${{ needs.tag.outputs.build-tag }}-bookworm-${{ matrix.arch }}
neondatabase/neon:${{ needs.tag.outputs.build-tag }}-${{ matrix.arch }}
neon-image:
needs: [ neon-image-arch, tag ]
@@ -583,9 +583,8 @@ jobs:
- name: Create multi-arch image
run: |
docker buildx imagetools create -t neondatabase/neon:${{ needs.tag.outputs.build-tag }} \
-t neondatabase/neon:${{ needs.tag.outputs.build-tag }}-bookworm \
neondatabase/neon:${{ needs.tag.outputs.build-tag }}-bookworm-x64 \
neondatabase/neon:${{ needs.tag.outputs.build-tag }}-bookworm-arm64
neondatabase/neon:${{ needs.tag.outputs.build-tag }}-x64 \
neondatabase/neon:${{ needs.tag.outputs.build-tag }}-arm64
- uses: docker/login-action@v3
with:
@@ -606,16 +605,17 @@ jobs:
version:
# Much data was already generated on old PG versions with bullseye's
# libraries, the locales of which can cause data incompatibilities.
# However, new PG versions should be build on newer images,
# as that reduces the support burden of old and ancient distros.
# However, new PG versions should check if they can be built on newer
# images, as that reduces the support burden of old and ancient
# distros.
- pg: v14
debian: bullseye
debian: bullseye-slim
- pg: v15
debian: bullseye
debian: bullseye-slim
- pg: v16
debian: bullseye
debian: bullseye-slim
- pg: v17
debian: bookworm
debian: bookworm-slim
arch: [ x64, arm64 ]
runs-on: ${{ fromJson(format('["self-hosted", "{0}"]', matrix.arch == 'arm64' && 'large-arm64' || 'large')) }}
@@ -625,7 +625,7 @@ jobs:
with:
submodules: true
- uses: neondatabase/dev-actions/set-docker-config-dir@6094485bf440001c94a94a3f9e221e81ff6b6193
- uses: ./.github/actions/set-docker-config-dir
- uses: docker/setup-buildx-action@v3
with:
cache-binary: false
@@ -660,19 +660,19 @@ jobs:
GIT_VERSION=${{ github.event.pull_request.head.sha || github.sha }}
PG_VERSION=${{ matrix.version.pg }}
BUILD_TAG=${{ needs.tag.outputs.build-tag }}
TAG=${{ needs.build-build-tools-image.outputs.image-tag }}-${{ matrix.version.debian }}
DEBIAN_VERSION=${{ matrix.version.debian }}
TAG=${{ needs.build-build-tools-image.outputs.image-tag }}
DEBIAN_FLAVOR=${{ matrix.version.debian }}
provenance: false
push: true
pull: true
file: compute/compute-node.Dockerfile
cache-from: type=registry,ref=cache.neon.build/compute-node-${{ matrix.version.pg }}:cache-${{ matrix.version.debian }}-${{ matrix.arch }}
cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/compute-node-{0}:cache-{1}-{2},mode=max', matrix.version.pg, matrix.version.debian, matrix.arch) || '' }}
file: compute/Dockerfile.compute-node
cache-from: type=registry,ref=cache.neon.build/compute-node-${{ matrix.version.pg }}:cache-${{ matrix.arch }}
cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/compute-node-{0}:cache-{1},mode=max', matrix.version.pg, matrix.arch) || '' }}
tags: |
neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-${{ matrix.arch }}
neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.arch }}
- name: Build neon extensions test image
if: matrix.version.pg >= 'v16'
if: matrix.version.pg == 'v16'
uses: docker/build-push-action@v6
with:
context: .
@@ -680,16 +680,17 @@ jobs:
GIT_VERSION=${{ github.event.pull_request.head.sha || github.sha }}
PG_VERSION=${{ matrix.version.pg }}
BUILD_TAG=${{ needs.tag.outputs.build-tag }}
TAG=${{ needs.build-build-tools-image.outputs.image-tag }}-${{ matrix.version.debian }}
DEBIAN_VERSION=${{ matrix.version.debian }}
TAG=${{ needs.build-build-tools-image.outputs.image-tag }}
DEBIAN_FLAVOR=${{ matrix.version.debian }}
provenance: false
push: true
pull: true
file: compute/compute-node.Dockerfile
file: compute/Dockerfile.compute-node
target: neon-pg-ext-test
cache-from: type=registry,ref=cache.neon.build/compute-node-${{ matrix.version.pg }}:cache-${{ matrix.version.debian }}-${{ matrix.arch }}
cache-from: type=registry,ref=cache.neon.build/neon-test-extensions-${{ matrix.version.pg }}:cache-${{ matrix.arch }}
cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/neon-test-extensions-{0}:cache-{1},mode=max', matrix.version.pg, matrix.arch) || '' }}
tags: |
neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{needs.tag.outputs.build-tag}}-${{ matrix.version.debian }}-${{ matrix.arch }}
neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{needs.tag.outputs.build-tag}}-${{ matrix.arch }}
- name: Build compute-tools image
# compute-tools are Postgres independent, so build it only once
@@ -704,16 +705,14 @@ jobs:
build-args: |
GIT_VERSION=${{ github.event.pull_request.head.sha || github.sha }}
BUILD_TAG=${{ needs.tag.outputs.build-tag }}
TAG=${{ needs.build-build-tools-image.outputs.image-tag }}-${{ matrix.version.debian }}
DEBIAN_VERSION=${{ matrix.version.debian }}
TAG=${{ needs.build-build-tools-image.outputs.image-tag }}
DEBIAN_FLAVOR=${{ matrix.version.debian }}
provenance: false
push: true
pull: true
file: compute/compute-node.Dockerfile
cache-from: type=registry,ref=cache.neon.build/compute-node-${{ matrix.version.pg }}:cache-${{ matrix.version.debian }}-${{ matrix.arch }}
cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/compute-tools-{0}:cache-{1}-{2},mode=max', matrix.version.pg, matrix.version.debian, matrix.arch) || '' }}
file: compute/Dockerfile.compute-node
tags: |
neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-${{ matrix.arch }}
neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-${{ matrix.arch }}
compute-node-image:
needs: [ compute-node-image-arch, tag ]
@@ -721,16 +720,7 @@ jobs:
strategy:
matrix:
version:
# see the comment for `compute-node-image-arch` job
- pg: v14
debian: bullseye
- pg: v15
debian: bullseye
- pg: v16
debian: bullseye
- pg: v17
debian: bookworm
version: [ v14, v15, v16, v17 ]
steps:
- uses: docker/login-action@v3
@@ -740,26 +730,23 @@ jobs:
- name: Create multi-arch compute-node image
run: |
docker buildx imagetools create -t neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }} \
-t neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }} \
neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-x64 \
neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-arm64
docker buildx imagetools create -t neondatabase/compute-node-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }} \
neondatabase/compute-node-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }}-x64 \
neondatabase/compute-node-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }}-arm64
- name: Create multi-arch neon-test-extensions image
if: matrix.version.pg >= 'v16'
if: matrix.version == 'v16'
run: |
docker buildx imagetools create -t neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }} \
-t neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }} \
neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-x64 \
neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-arm64
docker buildx imagetools create -t neondatabase/neon-test-extensions-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }} \
neondatabase/neon-test-extensions-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }}-x64 \
neondatabase/neon-test-extensions-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }}-arm64
- name: Create multi-arch compute-tools image
if: matrix.version.pg == 'v16'
if: matrix.version == 'v17'
run: |
docker buildx imagetools create -t neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }} \
-t neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }} \
neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-x64 \
neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-arm64
neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-x64 \
neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-arm64
- uses: docker/login-action@v3
with:
@@ -767,13 +754,13 @@ jobs:
username: ${{ secrets.AWS_ACCESS_KEY_DEV }}
password: ${{ secrets.AWS_SECRET_KEY_DEV }}
- name: Push multi-arch compute-node-${{ matrix.version.pg }} image to ECR
- name: Push multi-arch compute-node-${{ matrix.version }} image to ECR
run: |
docker buildx imagetools create -t 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }} \
neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}
docker buildx imagetools create -t 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-node-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }} \
neondatabase/compute-node-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }}
- name: Push multi-arch compute-tools image to ECR
if: matrix.version.pg == 'v16'
if: matrix.version == 'v17'
run: |
docker buildx imagetools create -t 369495373322.dkr.ecr.eu-central-1.amazonaws.com/compute-tools:${{ needs.tag.outputs.build-tag }} \
neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}
@@ -784,18 +771,9 @@ jobs:
strategy:
fail-fast: false
matrix:
version:
# see the comment for `compute-node-image-arch` job
- pg: v14
debian: bullseye
- pg: v15
debian: bullseye
- pg: v16
debian: bullseye
- pg: v17
debian: bookworm
version: [ v14, v15, v16, v17 ]
env:
VM_BUILDER_VERSION: v0.35.0
VM_BUILDER_VERSION: v0.29.3
steps:
- uses: actions/checkout@v4
@@ -805,7 +783,7 @@ jobs:
curl -fL https://github.com/neondatabase/autoscaling/releases/download/$VM_BUILDER_VERSION/vm-builder -o vm-builder
chmod +x vm-builder
- uses: neondatabase/dev-actions/set-docker-config-dir@6094485bf440001c94a94a3f9e221e81ff6b6193
- uses: ./.github/actions/set-docker-config-dir
- uses: docker/login-action@v3
with:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
@@ -815,19 +793,18 @@ jobs:
# it won't have the proper authentication (written at v0.6.0)
- name: Pulling compute-node image
run: |
docker pull neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}
docker pull neondatabase/compute-node-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }}
- name: Build vm image
run: |
./vm-builder \
-size=2G \
-spec=compute/vm-image-spec-${{ matrix.version.debian }}.yaml \
-src=neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }} \
-dst=neondatabase/vm-compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}
-spec=compute/vm-image-spec.yaml \
-src=neondatabase/compute-node-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }} \
-dst=neondatabase/vm-compute-node-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }}
- name: Pushing vm-compute-node image
run: |
docker push neondatabase/vm-compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}
docker push neondatabase/vm-compute-node-${{ matrix.version }}:${{ needs.tag.outputs.build-tag }}
test-images:
needs: [ check-permissions, tag, neon-image, compute-node-image ]
@@ -835,14 +812,13 @@ 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')) }}
steps:
- uses: actions/checkout@v4
- uses: neondatabase/dev-actions/set-docker-config-dir@6094485bf440001c94a94a3f9e221e81ff6b6193
- uses: ./.github/actions/set-docker-config-dir
- uses: docker/login-action@v3
with:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
@@ -874,10 +850,7 @@ jobs:
- name: Verify docker-compose example and test extensions
timeout-minutes: 20
env:
TAG: ${{needs.tag.outputs.build-tag}}
TEST_VERSION_ONLY: ${{ matrix.pg_version }}
run: ./docker-compose/docker_compose_test.sh
run: env TAG=${{needs.tag.outputs.build-tag}} ./docker-compose/docker_compose_test.sh
- name: Print logs and clean up
if: always()
@@ -937,7 +910,7 @@ jobs:
neondatabase/neon-test-extensions-v16:${{ needs.tag.outputs.build-tag }}
- name: Configure AWS-prod credentials
if: github.ref_name == 'release'|| github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
if: github.ref_name == 'release'|| github.ref_name == 'release-proxy'
uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: eu-central-1
@@ -946,12 +919,12 @@ jobs:
- name: Login to prod ECR
uses: docker/login-action@v3
if: github.ref_name == 'release'|| github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
if: github.ref_name == 'release'|| github.ref_name == 'release-proxy'
with:
registry: 093970136003.dkr.ecr.eu-central-1.amazonaws.com
- name: Copy all images to prod ECR
if: github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
if: github.ref_name == 'release'|| github.ref_name == 'release-proxy'
run: |
for image in neon compute-tools {vm-,}compute-node-{v14,v15,v16,v17}; do
docker buildx imagetools create -t 093970136003.dkr.ecr.eu-central-1.amazonaws.com/${image}:${{ needs.tag.outputs.build-tag }} \
@@ -971,7 +944,7 @@ jobs:
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'
if: github.ref_name == 'release'|| github.ref_name == 'release-proxy'
needs: [ tag, promote-images ]
uses: ./.github/workflows/_push-to-acr.yml
with:
@@ -1059,11 +1032,25 @@ jobs:
deploy:
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()
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:
- name: Fix git ownership
run: |
# Workaround for `fatal: detected dubious ownership in repository at ...`
#
# Use both ${{ github.workspace }} and ${GITHUB_WORKSPACE} because they're different on host and in containers
# Ref https://github.com/actions/checkout/issues/785
#
git config --global --add safe.directory ${{ github.workspace }}
git config --global --add safe.directory ${GITHUB_WORKSPACE}
for r in 14 15 16 17; do
git config --global --add safe.directory "${{ github.workspace }}/vendor/postgres-v$r"
git config --global --add safe.directory "${GITHUB_WORKSPACE}/vendor/postgres-v$r"
done
- uses: actions/checkout@v4
- name: Trigger deploy workflow
@@ -1072,6 +1059,7 @@ jobs:
run: |
if [[ "$GITHUB_REF_NAME" == "main" ]]; then
gh workflow --repo neondatabase/infra run deploy-dev.yml --ref main -f branch=main -f dockerTag=${{needs.tag.outputs.build-tag}} -f deployPreprodRegion=false
gh workflow --repo neondatabase/azure run deploy.yml -f dockerTag=${{needs.tag.outputs.build-tag}}
elif [[ "$GITHUB_REF_NAME" == "release" ]]; then
gh workflow --repo neondatabase/infra run deploy-dev.yml --ref main \
-f deployPgSniRouter=false \
@@ -1102,21 +1090,16 @@ jobs:
gh workflow --repo neondatabase/infra run deploy-proxy-prod.yml --ref main \
-f deployPgSniRouter=true \
-f deployProxyLink=true \
-f deployPrivatelinkProxy=true \
-f deployProxyScram=true \
-f deployProxyAuthBroker=true \
-f deployProxy=true \
-f branch=main \
-f dockerTag=${{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' || github.ref_name == 'release-compute'
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

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: |
${{ hashFiles('Dockerfile.build-tools',
'.github/workflows/check-build-tools-image.yml',
'.github/workflows/build-build-tools-image.yml') }}
run: |
echo "image-tag=${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

@@ -31,7 +31,7 @@ jobs:
runs-on: us-east-2
container:
image: neondatabase/build-tools:pinned-bookworm
image: neondatabase/build-tools:pinned
options: --init
steps:

View File

@@ -1,160 +0,0 @@
name: benchmarking ingest
on:
# uncomment to run on push for debugging your PR
# push:
# branches: [ your branch ]
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 9 * * *' # run once a day, timezone is utc
workflow_dispatch: # adds ability to run this manually
defaults:
run:
shell: bash -euxo pipefail {0}
concurrency:
# Allow only one workflow globally because we need dedicated resources which only exist once
group: ingest-bench-workflow
cancel-in-progress: true
jobs:
ingest:
strategy:
fail-fast: false # allow other variants to continue even if one fails
matrix:
target_project: [new_empty_project, large_existing_project]
permissions:
contents: write
statuses: write
id-token: write # aws-actions/configure-aws-credentials
env:
PG_CONFIG: /tmp/neon/pg_install/v16/bin/pg_config
PSQL: /tmp/neon/pg_install/v16/bin/psql
PG_16_LIB_PATH: /tmp/neon/pg_install/v16/lib
PGCOPYDB: /pgcopydb/bin/pgcopydb
PGCOPYDB_LIB_PATH: /pgcopydb/lib
runs-on: [ self-hosted, us-east-2, x64 ]
container:
image: neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
options: --init
timeout-minutes: 1440
steps:
- uses: actions/checkout@v4
- name: Configure AWS credentials # necessary to download artefacts
uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 18000 # 5 hours is currently max associated with IAM role
- name: Download Neon artifact
uses: ./.github/actions/download
with:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
- name: Create Neon 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: 16
compute_units: '[7, 7]' # we want to test large compute here to avoid compute-side bottleneck
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
- name: Initialize Neon project
if: ${{ matrix.target_project == 'new_empty_project' }}
env:
BENCHMARK_INGEST_TARGET_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
- name: Create Neon Branch for large tenant
if: ${{ matrix.target_project == 'large_existing_project' }}
id: create-neon-branch-ingest-target
uses: ./.github/actions/neon-branch-create
with:
project_id: ${{ vars.BENCHMARK_INGEST_TARGET_PROJECTID }}
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
- name: Initialize Neon project
if: ${{ matrix.target_project == 'large_existing_project' }}
env:
BENCHMARK_INGEST_TARGET_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="${BENCHMARK_INGEST_TARGET_CONNSTR%/*}"
# Extract the query parameters (if any) after the database name
query_params="${BENCHMARK_INGEST_TARGET_CONNSTR#*\?}"
# Reconstruct the new connection string
if [ "$query_params" != "$BENCHMARK_INGEST_TARGET_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}"
else
BENCHMARK_INGEST_TARGET_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
- 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: v16
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: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
- name: show tables sizes after ingest
run: |
export LD_LIBRARY_PATH=${PG_16_LIB_PATH}
${PSQL} "${BENCHMARK_INGEST_TARGET_CONNSTR}" -c "\dt+"
- name: Delete Neon 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 }}
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
- name: Delete Neon Branch for large tenant
if: ${{ always() && matrix.target_project == 'large_existing_project' }}
uses: ./.github/actions/neon-branch-delete
with:
project_id: ${{ vars.BENCHMARK_INGEST_TARGET_PROJECTID }}
branch_id: ${{ steps.create-neon-branch-ingest-target.outputs.branch_id }}
api_key: ${{ secrets.NEON_STAGING_API_KEY }}

View File

@@ -26,9 +26,15 @@ 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
check-macos-build:
@@ -38,7 +44,7 @@ jobs:
contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
github.ref_name == 'main'
timeout-minutes: 90
runs-on: macos-15
runs-on: macos-14
env:
# Use release build only, to have less debug info around
@@ -52,7 +58,7 @@ jobs:
submodules: true
- name: Install macOS postgres dependencies
run: brew install flex bison openssl protobuf icu4c
run: brew install flex bison openssl protobuf icu4c pkg-config
- name: Set pg 14 revision for caching
id: pg_v14_rev
@@ -149,7 +155,7 @@ jobs:
github.ref_name == 'main'
runs-on: [ self-hosted, large ]
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
image: ${{ needs.build-build-tools-image.outputs.image }}
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
@@ -195,8 +201,6 @@ jobs:
REPORT_URL: ${{ steps.upload-stats.outputs.report-url }}
SHA: ${{ github.event.pull_request.head.sha || github.sha }}
with:
# Retry script for 5XX server errors: https://github.com/actions/github-script#retries
retries: 5
script: |
const { REPORT_URL, SHA } = process.env

View File

@@ -29,7 +29,7 @@ jobs:
trigger_bench_on_ec2_machine_in_eu_central_1:
runs-on: [ self-hosted, small ]
container:
image: neondatabase/build-tools:pinned-bookworm
image: neondatabase/build-tools:pinned
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
@@ -72,7 +72,7 @@ jobs:
echo "COMMIT_HASH=$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}" \
@@ -116,7 +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: |
@@ -134,13 +134,13 @@ jobs:
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}" \

View File

@@ -39,9 +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:
@@ -49,7 +55,7 @@ jobs:
runs-on: ubuntu-22.04
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
image: ${{ needs.build-build-tools-image.outputs.image }}
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
@@ -144,7 +150,7 @@ jobs:
runs-on: ubuntu-22.04
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
image: ${{ needs.build-build-tools-image.outputs.image }}
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}

View File

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

View File

@@ -1,95 +0,0 @@
name: Pre-merge checks
on:
merge_group:
branches:
- main
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:
get-changed-files:
runs-on: ubuntu-22.04
outputs:
python-changed: ${{ steps.python-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
- name: PRINT ALL CHANGED FILES FOR DEBUG PURPOSES
env:
PYTHON_CHANGED_FILES: ${{ steps.python-src.outputs.all_changed_files }}
run: |
echo "${PYTHON_CHANGED_FILES}"
build-build-tools-image:
if: needs.get-changed-files.outputs.python-changed == 'true'
needs: [ get-changed-files ]
uses: ./.github/workflows/build-build-tools-image.yml
with:
# Build only one combination to save time
archs: '["x64"]'
debians: '["bookworm"]'
secrets: inherit
check-codestyle-python:
if: needs.get-changed-files.outputs.python-changed == 'true'
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: ${{ needs.build-build-tools-image.outputs.image }}-bookworm-x64
secrets: inherit
# To get items from the merge queue merged into main we need to satisfy "Status checks that are required".
# Currently we require 2 jobs (checks with exact name):
# - conclusion
# - neon-cloud-e2e
conclusion:
if: always()
permissions:
statuses: write # for `github.repos.createCommitStatus(...)`
needs:
- get-changed-files
- check-codestyle-python
runs-on: ubuntu-22.04
steps:
- name: Create fake `neon-cloud-e2e` check
uses: actions/github-script@v7
with:
# Retry script for 5XX server errors: https://github.com/actions/github-script#retries
retries: 5
script: |
const { repo, owner } = context.repo;
const targetUrl = `${context.serverUrl}/${owner}/${repo}/actions/runs/${context.runId}`;
await github.rest.repos.createCommitStatus({
owner: owner,
repo: repo,
sha: context.sha,
context: `neon-cloud-e2e`,
state: `success`,
target_url: targetUrl,
description: `fake check for merge queue`,
});
- name: Fail the job if any of the dependencies do not succeed or skipped
run: exit 1
if: |
(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

@@ -15,10 +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: {}
@@ -29,40 +25,83 @@ defaults:
jobs:
create-storage-release-branch:
if: ${{ github.event.schedule == '0 6 * * MON' || 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: ${{ secrets.CI_ACCESS_TOKEN }}
steps:
- name: Check out code
uses: actions/checkout@v4
with:
ref: main
create-compute-release-branch:
if: inputs.create-compute-release-branch
- name: Set environment variables
run: |
echo "RELEASE_DATE=$(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

@@ -1,53 +0,0 @@
name: Report Workflow Stats Batch
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 * * * *'
runs-on: ubuntu-22.04
permissions:
actions: read
steps:
- name: Export Workflow Run for the past 2 hours
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: '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
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: '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'

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 $CURRENT_SHA -w 'Build and Test' -L 1 --json databaseId --jq '.[].databaseId')
@@ -104,17 +102,12 @@ jobs:
# Default set of platforms to run e2e tests on
platforms='["docker", "k8s"]'
# If a PR changes anything that affects computes, add k8s-neonvm to the list of platforms.
# If the PR changes vendor/, pgxn/ or libs/vm_monitor/ directories, or compute/Dockerfile.compute-node, add k8s-neonvm to the list of platforms.
# If the workflow run is not a pull request, add k8s-neonvm to the list.
if [ "$GITHUB_EVENT_NAME" == "pull_request" ]; then
for f in $(gh api "/repos/${GITHUB_REPOSITORY}/pulls/${PR_NUMBER}/files" --paginate --jq '.[].filename'); do
case "$f" in
# List of directories that contain code which affect compute images.
#
# This isn't exhaustive, just the paths that are most directly compute-related.
# For example, compute_ctl also depends on libs/utils, but we don't trigger
# an e2e run on that.
vendor/*|pgxn/*|compute_tools/*|libs/vm_monitor/*|compute/compute-node.Dockerfile)
vendor/*|pgxn/*|libs/vm_monitor/*|compute/Dockerfile.compute-node)
platforms=$(echo "${platforms}" | jq --compact-output '. += ["k8s-neonvm"] | unique')
;;
*)

2
.gitignore vendored
View File

@@ -6,8 +6,6 @@ __pycache__/
test_output/
.vscode
.idea
*.swp
tags
neon.iml
/.neon
/integration_tests/.neon

View File

@@ -1,8 +1,7 @@
/.github/ @neondatabase/developer-productivity
/compute_tools/ @neondatabase/control-plane @neondatabase/compute
/storage_controller @neondatabase/storage
/libs/pageserver_api/ @neondatabase/storage
/libs/postgres_ffi/ @neondatabase/compute @neondatabase/storage
/libs/proxy/ @neondatabase/proxy
/libs/remote_storage/ @neondatabase/storage
/libs/safekeeper_api/ @neondatabase/storage
/libs/vm_monitor/ @neondatabase/autoscaling
@@ -11,6 +10,4 @@
/pgxn/neon/ @neondatabase/compute @neondatabase/storage
/proxy/ @neondatabase/proxy
/safekeeper/ @neondatabase/storage
/storage_controller @neondatabase/storage
/storage_scrubber @neondatabase/storage
/vendor/ @neondatabase/compute

1252
Cargo.lock generated

File diff suppressed because it is too large Load Diff

View File

@@ -33,11 +33,6 @@ members = [
"libs/postgres_ffi/wal_craft",
"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]
@@ -58,32 +53,30 @@ azure_storage_blobs = { version = "0.19", default-features = false, features = [
flate2 = "1.0.26"
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-config = { version = "1.3", default-features = false, features=["rustls"] }
aws-sdk-s3 = "1.26"
aws-sdk-iam = "1.15.0"
aws-smithy-async = { version = "1.2.1", default-features = false, features=["rt-tokio"] }
aws-smithy-types = "1.2"
aws-smithy-types = "1.1.9"
aws-credential-types = "1.2.0"
aws-sigv4 = { version = "1.2", features = ["sign-http"] }
aws-types = "1.3"
axum = { version = "0.7.5", features = ["ws"] }
aws-sigv4 = { version = "1.2.1", features = ["sign-http"] }
aws-types = "1.2.0"
axum = { version = "0.6.20", 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"] }
clap = { version = "4.0", features = ["derive"] }
comfy-table = "7.1"
const_format = "0.2"
crc32c = "0.6"
dashmap = { version = "5.5.0", features = ["raw-api"] }
diatomic-waker = { version = "0.2.3" }
either = "1.8"
enum-map = "2.4.2"
enumset = "1.0.12"
@@ -103,19 +96,14 @@ hmac = "0.12.1"
hostname = "0.4"
http = {version = "1.1.0", features = ["std"]}
http-types = { version = "2", default-features = false }
http-body-util = "0.1.2"
humantime = "2.1"
humantime-serde = "1.1.1"
hyper0 = { package = "hyper", version = "0.14" }
hyper = "1.4"
hyper-util = "0.1"
tokio-tungstenite = "0.21.0"
hyper = "0.14"
tokio-tungstenite = "0.20.0"
indexmap = "2"
indoc = "2"
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"
@@ -128,30 +116,28 @@ notify = "6.0.0"
num_cpus = "1.15"
num-traits = "0.2.15"
once_cell = "1.13"
opentelemetry = "0.26"
opentelemetry_sdk = "0.26"
opentelemetry-otlp = { version = "0.26", default-features=false, features = ["http-proto", "trace", "http", "reqwest-client"] }
opentelemetry-semantic-conventions = "0.26"
opentelemetry = "0.20.0"
opentelemetry-otlp = { version = "0.13.0", default-features=false, features = ["http-proto", "trace", "http", "reqwest-client"] }
opentelemetry-semantic-conventions = "0.12.0"
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", "protobuf", "protobuf-codec"] }
procfs = "0.16"
prometheus = {version = "0.13", default-features=false, features = ["process"]} # removes protobuf dependency
prost = "0.13"
prost = "0.11"
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_26"] }
reqwest-middleware = "0.4"
reqwest-retry = "0.7"
reqwest-tracing = { version = "0.5", features = ["opentelemetry_0_20"] }
reqwest-middleware = "0.3.0"
reqwest-retry = "0.5"
routerify = "3"
rpds = "0.13"
rustc-hash = "1.1.0"
rustls = { version = "0.23.16", default-features = false }
rustls = "0.22"
rustls-pemfile = "2"
scopeguard = "1.1"
sysinfo = "0.29.2"
@@ -161,7 +147,7 @@ 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"
@@ -176,23 +162,23 @@ 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"] }
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"
tokio-rustls = { version = "0.26.0", default-features = false, features = ["tls12", "ring"]}
tokio-postgres-rustls = "0.11.0"
tokio-rustls = "0.25"
tokio-stream = "0.1"
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", features = ["tls", "tls-roots"]}
tonic = {version = "0.9", features = ["tls", "tls-roots"]}
tower-service = "0.3.2"
tracing = "0.1"
tracing-error = "0.2"
tracing-opentelemetry = "0.27"
tracing-error = "0.2.0"
tracing-opentelemetry = "0.21.0"
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 }
@@ -201,33 +187,41 @@ url = "2.2"
urlencoding = "2.1"
uuid = { version = "1.6.1", features = ["v4", "v7", "serde"] }
walkdir = "2.3.2"
rustls-native-certs = "0.8"
x509-parser = "0.16"
rustls-native-certs = "0.7"
x509-parser = "0.15"
whoami = "1.5.1"
zerocopy = { version = "0.7", features = ["derive"] }
## TODO replace this with tracing
env_logger = "0.10"
log = "0.4"
## Libraries from neondatabase/ git forks, ideally with changes to be upstreamed
postgres = { git = "https://github.com/neondatabase/rust-postgres.git", 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" }
# 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" }
@@ -239,22 +233,21 @@ tracing-utils = { version = "0.1", path = "./libs/tracing-utils/" }
utils = { version = "0.1", path = "./libs/utils/" }
vm_monitor = { version = "0.1", path = "./libs/vm_monitor/" }
walproposer = { version = "0.1", path = "./libs/walproposer/" }
wal_decoder = { version = "0.1", path = "./libs/wal_decoder" }
## Common library dependency
workspace_hack = { version = "0.1", path = "./workspace_hack/" }
## Build dependencies
criterion = "0.5.1"
rcgen = "0.13"
rcgen = "0.12"
rstest = "0.18"
camino-tempfile = "1.0.2"
tonic-build = "0.12"
tonic-build = "0.9"
[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

View File

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

View File

@@ -1,70 +1,18 @@
ARG DEBIAN_VERSION=bookworm
FROM debian:bullseye-slim
FROM debian:bookworm-slim AS pgcopydb_builder
ARG DEBIAN_VERSION
RUN if [ "${DEBIAN_VERSION}" = "bookworm" ]; then \
set -e && \
apt update && \
apt install -y --no-install-recommends \
ca-certificates wget gpg && \
wget -qO - https://www.postgresql.org/media/keys/ACCC4CF8.asc | gpg --dearmor -o /usr/share/keyrings/postgresql-keyring.gpg && \
echo "deb [signed-by=/usr/share/keyrings/postgresql-keyring.gpg] http://apt.postgresql.org/pub/repos/apt bookworm-pgdg main" > /etc/apt/sources.list.d/pgdg.list && \
apt-get update && \
apt install -y --no-install-recommends \
build-essential \
autotools-dev \
libedit-dev \
libgc-dev \
libpam0g-dev \
libreadline-dev \
libselinux1-dev \
libxslt1-dev \
libssl-dev \
libkrb5-dev \
zlib1g-dev \
liblz4-dev \
libpq5 \
libpq-dev \
libzstd-dev \
postgresql-16 \
postgresql-server-dev-16 \
postgresql-common \
python3-sphinx && \
wget -O /tmp/pgcopydb.tar.gz https://github.com/dimitri/pgcopydb/archive/refs/tags/v0.17.tar.gz && \
mkdir /tmp/pgcopydb && \
tar -xzf /tmp/pgcopydb.tar.gz -C /tmp/pgcopydb --strip-components=1 && \
cd /tmp/pgcopydb && \
make -s clean && \
make -s -j12 install && \
libpq_path=$(find /lib /usr/lib -name "libpq.so.5" | head -n 1) && \
mkdir -p /pgcopydb/lib && \
cp "$libpq_path" /pgcopydb/lib/; \
else \
# copy command below will fail if we don't have dummy files, so we create them for other debian versions
mkdir -p /usr/lib/postgresql/16/bin && touch /usr/lib/postgresql/16/bin/pgcopydb && \
mkdir -p mkdir -p /pgcopydb/lib && touch /pgcopydb/lib/libpq.so.5; \
fi
FROM debian:${DEBIAN_VERSION}-slim AS build_tools
ARG DEBIAN_VERSION
# Use ARG as a build-time environment variable here to allow.
# It's not supposed to be set outside.
# Alternatively it can be obtained using the following command
# ```
# . /etc/os-release && echo "${VERSION_CODENAME}"
# ```
ARG DEBIAN_VERSION_CODENAME=bullseye
# Add nonroot user
RUN useradd -ms /bin/bash nonroot -b /home
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
# System deps
#
# 'gdb' is included so that we get backtraces of core dumps produced in
# regression tests
RUN set -e \
&& apt update \
&& apt install -y \
@@ -76,12 +24,10 @@ RUN set -e \
cmake \
curl \
flex \
gdb \
git \
gnupg \
gzip \
jq \
jsonnet \
libcurl4-openssl-dev \
libbz2-dev \
libffi-dev \
@@ -92,14 +38,14 @@ RUN set -e \
libseccomp-dev \
libsqlite3-dev \
libssl-dev \
$([[ "${DEBIAN_VERSION}" = "bullseye" ]] && echo libstdc++-10-dev || echo libstdc++-11-dev) \
libstdc++-10-dev \
libtool \
libxml2-dev \
libxmlsec1-dev \
libxxhash-dev \
lsof \
make \
netcat-openbsd \
netcat \
net-tools \
openssh-client \
parallel \
@@ -111,18 +57,6 @@ RUN set -e \
zstd \
&& rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
# sql_exporter
# Keep the version the same as in compute/compute-node.Dockerfile and
# test_runner/regress/test_compute_metrics.py.
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 \
&& mkdir /tmp/sql_exporter \
&& tar xzvf sql_exporter.tar.gz -C /tmp/sql_exporter --strip-components=1 \
&& mv /tmp/sql_exporter/sql_exporter /usr/local/bin/sql_exporter
# protobuf-compiler (protoc)
ENV PROTOC_VERSION=25.1
RUN curl -fsSL "https://github.com/protocolbuffers/protobuf/releases/download/v${PROTOC_VERSION}/protoc-${PROTOC_VERSION}-linux-$(uname -m | sed 's/aarch64/aarch_64/g').zip" -o "protoc.zip" \
@@ -138,9 +72,9 @@ RUN curl -sL "https://github.com/peak/s5cmd/releases/download/v${S5CMD_VERSION}/
&& mv s5cmd /usr/local/bin/s5cmd
# LLVM
ENV LLVM_VERSION=19
ENV LLVM_VERSION=18
RUN curl -fsSL 'https://apt.llvm.org/llvm-snapshot.gpg.key' | apt-key add - \
&& echo "deb http://apt.llvm.org/${DEBIAN_VERSION}/ llvm-toolchain-${DEBIAN_VERSION}-${LLVM_VERSION} main" > /etc/apt/sources.list.d/llvm.stable.list \
&& echo "deb http://apt.llvm.org/${DEBIAN_VERSION_CODENAME}/ llvm-toolchain-${DEBIAN_VERSION_CODENAME}-${LLVM_VERSION} main" > /etc/apt/sources.list.d/llvm.stable.list \
&& apt update \
&& apt install -y clang-${LLVM_VERSION} llvm-${LLVM_VERSION} \
&& bash -c 'for f in /usr/bin/clang*-${LLVM_VERSION} /usr/bin/llvm*-${LLVM_VERSION}; do ln -s "${f}" "${f%-${LLVM_VERSION}}"; done' \
@@ -148,7 +82,7 @@ RUN curl -fsSL 'https://apt.llvm.org/llvm-snapshot.gpg.key' | apt-key add - \
# Install docker
RUN curl -fsSL https://download.docker.com/linux/ubuntu/gpg | gpg --dearmor -o /usr/share/keyrings/docker-archive-keyring.gpg \
&& echo "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/docker-archive-keyring.gpg] https://download.docker.com/linux/debian ${DEBIAN_VERSION} stable" > /etc/apt/sources.list.d/docker.list \
&& echo "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/docker-archive-keyring.gpg] https://download.docker.com/linux/debian ${DEBIAN_VERSION_CODENAME} stable" > /etc/apt/sources.list.d/docker.list \
&& apt update \
&& apt install -y docker-ce docker-ce-cli \
&& rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
@@ -165,7 +99,7 @@ RUN curl "https://awscli.amazonaws.com/awscli-exe-linux-$(uname -m).zip" -o "aws
&& rm awscliv2.zip
# Mold: A Modern Linker
ENV MOLD_VERSION=v2.34.1
ENV MOLD_VERSION=v2.33.0
RUN set -e \
&& git clone https://github.com/rui314/mold.git \
&& mkdir mold/build \
@@ -208,7 +142,7 @@ RUN wget -O /tmp/openssl-${OPENSSL_VERSION}.tar.gz https://www.openssl.org/sourc
# Use the same version of libicu as the compute nodes so that
# clusters created using inidb on pageserver can be used by computes.
#
# TODO: at this time, compute-node.Dockerfile uses the debian bullseye libicu
# TODO: at this time, Dockerfile.compute-node uses the debian bullseye libicu
# package, which is 67.1. We're duplicating that knowledge here, and also, technically,
# Debian has a few patches on top of 67.1 that we're not adding here.
ENV ICU_VERSION=67.1
@@ -234,7 +168,7 @@ USER nonroot:nonroot
WORKDIR /home/nonroot
# Python
ENV PYTHON_VERSION=3.11.10 \
ENV PYTHON_VERSION=3.9.19 \
PYENV_ROOT=/home/nonroot/.pyenv \
PATH=/home/nonroot/.pyenv/shims:/home/nonroot/.pyenv/bin:/home/nonroot/.poetry/bin:$PATH
RUN set -e \
@@ -258,14 +192,14 @@ 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=1.83.0
ENV RUSTC_VERSION=1.81.0
ENV RUSTUP_HOME="/home/nonroot/.rustup"
ENV PATH="/home/nonroot/.cargo/bin:${PATH}"
ARG RUSTFILT_VERSION=0.2.1
ARG CARGO_HAKARI_VERSION=0.9.33
ARG CARGO_DENY_VERSION=0.16.2
ARG CARGO_HACK_VERSION=0.6.33
ARG CARGO_NEXTEST_VERSION=0.9.85
ARG CARGO_HAKARI_VERSION=0.9.30
ARG CARGO_DENY_VERSION=0.16.1
ARG CARGO_HACK_VERSION=0.6.31
ARG CARGO_NEXTEST_VERSION=0.9.72
RUN curl -sSO https://static.rust-lang.org/rustup/dist/$(uname -m)-unknown-linux-gnu/rustup-init && whoami && \
chmod +x rustup-init && \
./rustup-init -y --default-toolchain ${RUSTC_VERSION} && \
@@ -291,11 +225,5 @@ RUN whoami \
&& rustc --version --verbose \
&& clang --version
RUN if [ "${DEBIAN_VERSION}" = "bookworm" ]; then \
LD_LIBRARY_PATH=/pgcopydb/lib /pgcopydb/bin/pgcopydb --version; \
else \
echo "pgcopydb is not available for ${DEBIAN_VERSION}"; \
fi
# Set following flag to check in Makefile if its running in Docker
RUN touch /home/nonroot/.docker_build

View File

@@ -38,7 +38,6 @@ ifeq ($(UNAME_S),Linux)
# Seccomp BPF is only available for Linux
PG_CONFIGURE_OPTS += --with-libseccomp
else ifeq ($(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
@@ -147,8 +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 $*"
@@ -171,27 +168,27 @@ postgres-check-%: postgres-%
neon-pg-ext-%: postgres-%
+@echo "Compiling neon $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile install
+@echo "Compiling neon_walredo $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-walredo-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-walredo-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_walredo/Makefile install
+@echo "Compiling neon_rmgr $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-rmgr-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-rmgr-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_rmgr/Makefile install
+@echo "Compiling neon_test_utils $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_test_utils/Makefile install
+@echo "Compiling neon_utils $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-utils-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-utils-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_utils/Makefile install
@@ -223,7 +220,7 @@ neon-pg-clean-ext-%:
walproposer-lib: neon-pg-ext-v17
+@echo "Compiling walproposer-lib"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/walproposer-lib
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v17/bin/pg_config COPT='$(COPT)' \
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v17/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/walproposer-lib \
-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile walproposer-lib
cp $(POSTGRES_INSTALL_DIR)/v17/lib/libpgport.a $(POSTGRES_INSTALL_DIR)/build/walproposer-lib
@@ -294,13 +291,12 @@ postgres-check: \
# This doesn't remove the effects of 'configure'.
.PHONY: clean
clean: postgres-clean neon-pg-clean-ext
$(MAKE) -C compute clean
$(CARGO_CMD_PREFIX) cargo clean
# This removes everything
.PHONY: distclean
distclean:
$(RM) -r $(POSTGRES_INSTALL_DIR)
rm -rf $(POSTGRES_INSTALL_DIR)
$(CARGO_CMD_PREFIX) cargo clean
.PHONY: fmt
@@ -332,12 +328,12 @@ postgres-%-pgindent: postgres-%-pg-bsd-indent postgres-%-typedefs.list
$(ROOT_PROJECT_DIR)/vendor/postgres-$*/src/tools/pgindent/pgindent --typedefs postgres-$*-typedefs-full.list \
$(ROOT_PROJECT_DIR)/vendor/postgres-$*/src/ \
--excludes $(ROOT_PROJECT_DIR)/vendor/postgres-$*/src/tools/pgindent/exclude_file_patterns
$(RM) pg*.BAK
rm -f pg*.BAK
# Indent pxgn/neon.
.PHONY: neon-pgindent
neon-pgindent: postgres-v17-pg-bsd-indent neon-pg-ext-v17
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v17/bin/pg_config COPT='$(COPT)' \
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v17/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
FIND_TYPEDEF=$(ROOT_PROJECT_DIR)/vendor/postgres-v17/src/tools/find_typedef \
INDENT=$(POSTGRES_INSTALL_DIR)/build/v17/src/tools/pg_bsd_indent/pg_bsd_indent \
PGINDENT_SCRIPT=$(ROOT_PROJECT_DIR)/vendor/postgres-v17/src/tools/pgindent/pgindent \

View File

@@ -31,7 +31,7 @@ See developer documentation in [SUMMARY.md](/docs/SUMMARY.md) for more informati
```bash
apt install build-essential libtool libreadline-dev zlib1g-dev flex bison libseccomp-dev \
libssl-dev clang pkg-config libpq-dev cmake postgresql-client protobuf-compiler \
libprotobuf-dev libcurl4-openssl-dev openssl python3-poetry lsof libicu-dev
libcurl4-openssl-dev openssl python3-poetry lsof libicu-dev
```
* On Fedora, these packages are needed:
```bash
@@ -58,7 +58,7 @@ curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
1. Install XCode and dependencies
```
xcode-select --install
brew install protobuf openssl flex bison icu4c pkg-config m4
brew install protobuf openssl flex bison icu4c pkg-config
# add openssl to PATH, required for ed25519 keys generation in neon_local
echo 'export PATH="$(brew --prefix openssl)/bin:$PATH"' >> ~/.zshrc
@@ -132,7 +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

5
compute/.gitignore vendored
View File

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

View File

@@ -1,50 +0,0 @@
jsonnet_files = $(wildcard \
etc/*.jsonnet \
etc/sql_exporter/*.libsonnet)
.PHONY: all
all: neon_collector.yml neon_collector_autoscaling.yml sql_exporter.yml sql_exporter_autoscaling.yml
neon_collector.yml: $(jsonnet_files)
JSONNET_PATH=jsonnet:etc jsonnet \
--output-file etc/$@ \
--ext-str pg_version=$(PG_VERSION) \
etc/neon_collector.jsonnet
neon_collector_autoscaling.yml: $(jsonnet_files)
JSONNET_PATH=jsonnet:etc jsonnet \
--output-file etc/$@ \
--ext-str pg_version=$(PG_VERSION) \
etc/neon_collector_autoscaling.jsonnet
sql_exporter.yml: $(jsonnet_files)
JSONNET_PATH=etc jsonnet \
--output-file etc/$@ \
--tla-str collector_name=neon_collector \
--tla-str collector_file=neon_collector.yml \
--tla-str 'connection_string=postgresql://cloud_admin@127.0.0.1:5432/postgres?sslmode=disable&application_name=sql_exporter' \
etc/sql_exporter.jsonnet
sql_exporter_autoscaling.yml: $(jsonnet_files)
JSONNET_PATH=etc jsonnet \
--output-file etc/$@ \
--tla-str collector_name=neon_collector_autoscaling \
--tla-str collector_file=neon_collector_autoscaling.yml \
--tla-str 'connection_string=postgresql://cloud_admin@127.0.0.1:5432/postgres?sslmode=disable&application_name=sql_exporter_autoscaling' \
etc/sql_exporter.jsonnet
.PHONY: clean
clean:
$(RM) \
etc/neon_collector.yml \
etc/neon_collector_autoscaling.yml \
etc/sql_exporter.yml \
etc/sql_exporter_autoscaling.yml
.PHONY: jsonnetfmt-test
jsonnetfmt-test:
jsonnetfmt --test $(jsonnet_files)
.PHONY: jsonnetfmt-format
jsonnetfmt-format:
jsonnetfmt --in-place $(jsonnet_files)

View File

@@ -1,7 +1,7 @@
This directory contains files that are needed to build the compute
images, or included in the compute images.
compute-node.Dockerfile
Dockerfile.compute-node
To build the compute image
vm-image-spec.yaml
@@ -14,8 +14,8 @@ etc/
patches/
Some extensions need to be patched to work with Neon. This
directory contains such patches. They are applied to the extension
sources in compute-node.Dockerfile
sources in Dockerfile.compute-node
In addition to these, postgres itself, the neon postgres extension,
and compute_ctl are built and copied into the compute image by
compute-node.Dockerfile.
Dockerfile.compute-node.

View File

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

View File

@@ -1,54 +0,0 @@
{
collector_name: 'neon_collector',
metrics: [
import 'sql_exporter/checkpoints_req.libsonnet',
import 'sql_exporter/checkpoints_timed.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',
import 'sql_exporter/db_total_size.libsonnet',
import 'sql_exporter/file_cache_read_wait_seconds_bucket.libsonnet',
import 'sql_exporter/file_cache_read_wait_seconds_count.libsonnet',
import 'sql_exporter/file_cache_read_wait_seconds_sum.libsonnet',
import 'sql_exporter/file_cache_write_wait_seconds_bucket.libsonnet',
import 'sql_exporter/file_cache_write_wait_seconds_count.libsonnet',
import 'sql_exporter/file_cache_write_wait_seconds_sum.libsonnet',
import 'sql_exporter/getpage_prefetch_discards_total.libsonnet',
import 'sql_exporter/getpage_prefetch_misses_total.libsonnet',
import 'sql_exporter/getpage_prefetch_requests_total.libsonnet',
import 'sql_exporter/getpage_prefetches_buffered.libsonnet',
import 'sql_exporter/getpage_sync_requests_total.libsonnet',
import 'sql_exporter/getpage_wait_seconds_bucket.libsonnet',
import 'sql_exporter/getpage_wait_seconds_count.libsonnet',
import 'sql_exporter/getpage_wait_seconds_sum.libsonnet',
import 'sql_exporter/lfc_approximate_working_set_size.libsonnet',
import 'sql_exporter/lfc_approximate_working_set_size_windows.libsonnet',
import 'sql_exporter/lfc_cache_size_limit.libsonnet',
import 'sql_exporter/lfc_hits.libsonnet',
import 'sql_exporter/lfc_misses.libsonnet',
import 'sql_exporter/lfc_used.libsonnet',
import 'sql_exporter/lfc_writes.libsonnet',
import 'sql_exporter/logical_slot_restart_lsn.libsonnet',
import 'sql_exporter/max_cluster_size.libsonnet',
import 'sql_exporter/pageserver_disconnects_total.libsonnet',
import 'sql_exporter/pageserver_requests_sent_total.libsonnet',
import 'sql_exporter/pageserver_send_flushes_total.libsonnet',
import 'sql_exporter/pageserver_open_requests.libsonnet',
import 'sql_exporter/pg_stats_userdb.libsonnet',
import 'sql_exporter/replication_delay_bytes.libsonnet',
import 'sql_exporter/replication_delay_seconds.libsonnet',
import 'sql_exporter/retained_wal.libsonnet',
import 'sql_exporter/wal_is_lost.libsonnet',
],
queries: [
{
query_name: 'neon_perf_counters',
query: importstr 'sql_exporter/neon_perf_counters.sql',
},
],
}

View File

@@ -0,0 +1,246 @@
collector_name: neon_collector
metrics:
- metric_name: lfc_misses
type: gauge
help: 'lfc_misses'
key_labels:
values: [lfc_misses]
query: |
select lfc_value as lfc_misses from neon.neon_lfc_stats where lfc_key='file_cache_misses';
- metric_name: lfc_used
type: gauge
help: 'LFC chunks used (chunk = 1MB)'
key_labels:
values: [lfc_used]
query: |
select lfc_value as lfc_used from neon.neon_lfc_stats where lfc_key='file_cache_used';
- metric_name: lfc_hits
type: gauge
help: 'lfc_hits'
key_labels:
values: [lfc_hits]
query: |
select lfc_value as lfc_hits from neon.neon_lfc_stats where lfc_key='file_cache_hits';
- metric_name: lfc_writes
type: gauge
help: 'lfc_writes'
key_labels:
values: [lfc_writes]
query: |
select lfc_value as lfc_writes from neon.neon_lfc_stats where lfc_key='file_cache_writes';
- metric_name: lfc_cache_size_limit
type: gauge
help: 'LFC cache size limit in bytes'
key_labels:
values: [lfc_cache_size_limit]
query: |
select pg_size_bytes(current_setting('neon.file_cache_size_limit')) as lfc_cache_size_limit;
- metric_name: connection_counts
type: gauge
help: 'Connection counts'
key_labels:
- datname
- state
values: [count]
query: |
select datname, state, count(*) as count from pg_stat_activity where state <> '' group by datname, state;
- metric_name: pg_stats_userdb
type: gauge
help: 'Stats for several oldest non-system dbs'
key_labels:
- datname
value_label: kind
values:
- db_size
- deadlocks
# Rows
- inserted
- updated
- deleted
# We export stats for 10 non-system database. Without this limit
# it is too easy to abuse the system by creating lots of databases.
query: |
select pg_database_size(datname) as db_size, deadlocks,
tup_inserted as inserted, tup_updated as updated, tup_deleted as deleted,
datname
from pg_stat_database
where datname IN (
select datname
from pg_database
where datname <> 'postgres' and not datistemplate
order by oid
limit 10
);
- metric_name: max_cluster_size
type: gauge
help: 'neon.max_cluster_size setting'
key_labels:
values: [max_cluster_size]
query: |
select setting::int as max_cluster_size from pg_settings where name = 'neon.max_cluster_size';
- metric_name: db_total_size
type: gauge
help: 'Size of all databases'
key_labels:
values: [total]
query: |
select sum(pg_database_size(datname)) as total from pg_database;
# DEPRECATED
- metric_name: lfc_approximate_working_set_size
type: gauge
help: 'Approximate working set size in pages of 8192 bytes'
key_labels:
values: [approximate_working_set_size]
query: |
select neon.approximate_working_set_size(false) as approximate_working_set_size;
- metric_name: lfc_approximate_working_set_size_windows
type: gauge
help: 'Approximate working set size in pages of 8192 bytes'
key_labels: [duration]
values: [size]
# NOTE: This is the "public" / "human-readable" version. Here, we supply a small selection
# of durations in a pretty-printed form.
query: |
select
x as duration,
neon.approximate_working_set_size_seconds(extract('epoch' from x::interval)::int) as size
from
(values ('5m'),('15m'),('1h')) as t (x);
- metric_name: compute_current_lsn
type: gauge
help: 'Current LSN of the database'
key_labels:
values: [lsn]
query: |
select
case
when pg_catalog.pg_is_in_recovery()
then (pg_last_wal_replay_lsn() - '0/0')::FLOAT8
else (pg_current_wal_lsn() - '0/0')::FLOAT8
end as lsn;
- metric_name: compute_receive_lsn
type: gauge
help: 'Returns the last write-ahead log location that has been received and synced to disk by streaming replication'
key_labels:
values: [lsn]
query: |
SELECT
CASE
WHEN pg_catalog.pg_is_in_recovery()
THEN (pg_last_wal_receive_lsn() - '0/0')::FLOAT8
ELSE 0
END AS lsn;
- metric_name: replication_delay_bytes
type: gauge
help: 'Bytes between received and replayed LSN'
key_labels:
values: [replication_delay_bytes]
# We use a GREATEST call here because this calculation can be negative.
# The calculation is not atomic, meaning after we've gotten the receive
# LSN, the replay LSN may have advanced past the receive LSN we
# are using for the calculation.
query: |
SELECT GREATEST(0, pg_wal_lsn_diff(pg_last_wal_receive_lsn(), pg_last_wal_replay_lsn())) AS replication_delay_bytes;
- metric_name: replication_delay_seconds
type: gauge
help: 'Time since last LSN was replayed'
key_labels:
values: [replication_delay_seconds]
query: |
SELECT
CASE
WHEN pg_last_wal_receive_lsn() = pg_last_wal_replay_lsn() THEN 0
ELSE GREATEST (0, EXTRACT (EPOCH FROM now() - pg_last_xact_replay_timestamp()))
END AS replication_delay_seconds;
- metric_name: checkpoints_req
type: gauge
help: 'Number of requested checkpoints'
key_labels:
values: [checkpoints_req]
query: |
SELECT checkpoints_req FROM pg_stat_bgwriter;
- metric_name: checkpoints_timed
type: gauge
help: 'Number of scheduled checkpoints'
key_labels:
values: [checkpoints_timed]
query: |
SELECT checkpoints_timed FROM pg_stat_bgwriter;
- metric_name: compute_logical_snapshot_files
type: gauge
help: 'Number of snapshot files in pg_logical/snapshot'
key_labels:
- timeline_id
values: [num_logical_snapshot_files]
query: |
SELECT
(SELECT setting FROM pg_settings WHERE name = 'neon.timeline_id') AS timeline_id,
-- Postgres creates temporary snapshot files of the form %X-%X.snap.%d.tmp. These
-- temporary snapshot files are renamed to the actual snapshot files after they are
-- completely built. We only WAL-log the completely built snapshot files.
(SELECT COUNT(*) FROM pg_ls_dir('pg_logical/snapshots') AS name WHERE name LIKE '%.snap') AS num_logical_snapshot_files;
# In all the below metrics, we cast LSNs to floats because Prometheus only supports floats.
# It's probably fine because float64 can store integers from -2^53 to +2^53 exactly.
# Number of slots is limited by max_replication_slots, so collecting position for all of them shouldn't be bad.
- metric_name: logical_slot_restart_lsn
type: gauge
help: 'restart_lsn of logical slots'
key_labels:
- slot_name
values: [restart_lsn]
query: |
select slot_name, (restart_lsn - '0/0')::FLOAT8 as restart_lsn
from pg_replication_slots
where slot_type = 'logical';
- metric_name: compute_subscriptions_count
type: gauge
help: 'Number of logical replication subscriptions grouped by enabled/disabled'
key_labels:
- enabled
values: [subscriptions_count]
query: |
select subenabled::text as enabled, count(*) as subscriptions_count
from pg_subscription
group by subenabled;
- metric_name: retained_wal
type: gauge
help: 'Retained WAL in inactive replication slots'
key_labels:
- slot_name
values: [retained_wal]
query: |
SELECT slot_name, pg_wal_lsn_diff(pg_current_wal_lsn(), restart_lsn)::FLOAT8 AS retained_wal
FROM pg_replication_slots
WHERE active = false;
- metric_name: wal_is_lost
type: gauge
help: 'Whether or not the replication slot wal_status is lost'
key_labels:
- slot_name
values: [wal_is_lost]
query: |
SELECT slot_name,
CASE WHEN wal_status = 'lost' THEN 1 ELSE 0 END AS wal_is_lost
FROM pg_replication_slots;

View File

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

View File

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

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

View File

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

View File

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

View File

@@ -1 +0,0 @@
SELECT num_requested AS checkpoints_req FROM pg_stat_checkpointer;

View File

@@ -1,15 +0,0 @@
local neon = import 'neon.libsonnet';
local pg_stat_bgwriter = importstr 'sql_exporter/checkpoints_req.sql';
local pg_stat_checkpointer = importstr 'sql_exporter/checkpoints_req.17.sql';
{
metric_name: 'checkpoints_req',
type: 'gauge',
help: 'Number of requested checkpoints',
key_labels: null,
values: [
'checkpoints_req',
],
query: if neon.PG_MAJORVERSION_NUM < 17 then pg_stat_bgwriter else pg_stat_checkpointer,
}

View File

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

View File

@@ -1 +0,0 @@
SELECT num_timed AS checkpoints_timed FROM pg_stat_checkpointer;

View File

@@ -1,15 +0,0 @@
local neon = import 'neon.libsonnet';
local pg_stat_bgwriter = importstr 'sql_exporter/checkpoints_timed.sql';
local pg_stat_checkpointer = importstr 'sql_exporter/checkpoints_timed.17.sql';
{
metric_name: 'checkpoints_timed',
type: 'gauge',
help: 'Number of scheduled checkpoints',
key_labels: null,
values: [
'checkpoints_timed',
],
query: if neon.PG_MAJORVERSION_NUM < 17 then pg_stat_bgwriter else pg_stat_checkpointer,
}

View File

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

View File

@@ -1,10 +0,0 @@
{
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.sql',
}

View File

@@ -1 +0,0 @@
SELECT (neon.backpressure_throttling_time()::float8 / 1000000) AS throttled;

View File

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

View File

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

View File

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

View File

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

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

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

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