Compare commits

..

1 Commits

Author SHA1 Message Date
Vlad Lazar
750d65fa77 [WIP] Add logs for pg-regress 2025-04-25 16:38:08 +02:00
677 changed files with 12495 additions and 35122 deletions

View File

@@ -33,14 +33,9 @@ config-variables:
- REMOTE_STORAGE_AZURE_CONTAINER
- REMOTE_STORAGE_AZURE_REGION
- SLACK_CICD_CHANNEL_ID
- SLACK_COMPUTE_CHANNEL_ID
- SLACK_ON_CALL_DEVPROD_STREAM
- SLACK_ON_CALL_QA_STAGING_STREAM
- SLACK_ON_CALL_STORAGE_STAGING_STREAM
- SLACK_ONCALL_COMPUTE_GROUP
- SLACK_ONCALL_PROXY_GROUP
- SLACK_ONCALL_STORAGE_GROUP
- SLACK_PROXY_CHANNEL_ID
- SLACK_RUST_CHANNEL_ID
- SLACK_STORAGE_CHANNEL_ID
- SLACK_UPCOMING_RELEASE_CHANNEL_ID

View File

@@ -7,7 +7,7 @@ inputs:
type: boolean
required: false
default: false
aws-oidc-role-arn:
aws-oicd-role-arn:
description: 'OIDC role arn to interract with S3'
required: true
@@ -88,7 +88,7 @@ runs:
if: ${{ !cancelled() }}
with:
aws-region: eu-central-1
role-to-assume: ${{ inputs.aws-oidc-role-arn }}
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

View File

@@ -8,7 +8,7 @@ inputs:
unique-key:
description: 'string to distinguish different results in the same run'
required: true
aws-oidc-role-arn:
aws-oicd-role-arn:
description: 'OIDC role arn to interract with S3'
required: true
@@ -39,7 +39,7 @@ runs:
if: ${{ !cancelled() }}
with:
aws-region: eu-central-1
role-to-assume: ${{ inputs.aws-oidc-role-arn }}
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

View File

@@ -15,7 +15,7 @@ inputs:
prefix:
description: "S3 prefix. Default is '${GITHUB_RUN_ID}/${GITHUB_RUN_ATTEMPT}'"
required: false
aws-oidc-role-arn:
aws-oicd-role-arn:
description: 'OIDC role arn to interract with S3'
required: true
@@ -25,7 +25,7 @@ runs:
- uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: eu-central-1
role-to-assume: ${{ inputs.aws-oidc-role-arn }}
role-to-assume: ${{ inputs.aws-oicd-role-arn }}
role-duration-seconds: 3600
- name: Download artifact

View File

@@ -66,9 +66,9 @@ runs:
# A shell without `set -x` to not to expose password/dsn in logs
shell: bash -euo pipefail {0}
run: |
res=$(curl \
project=$(curl \
"https://${API_HOST}/api/v2/projects" \
-w "%{http_code}" \
--fail \
--header "Accept: application/json" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${API_KEY}" \
@@ -83,15 +83,6 @@ runs:
\"settings\": ${PROJECT_SETTINGS}
}
}")
code=${res: -3}
if [[ ${code} -ge 400 ]]; then
echo Request failed with error code ${code}
echo ${res::-3}
exit 1
else
project=${res::-3}
fi
# Mask password
echo "::add-mask::$(echo $project | jq --raw-output '.roles[] | select(.name != "web_access") | .password')"
@@ -135,7 +126,6 @@ runs:
-H "Accept: application/json" -H "Content-Type: application/json" -H "Authorization: Bearer ${ADMIN_API_KEY}" \
-d "{\"scheduling\": \"Essential\"}"
fi
env:
API_HOST: ${{ inputs.api_host }}

View File

@@ -53,7 +53,7 @@ inputs:
description: 'benchmark durations JSON'
required: false
default: '{}'
aws-oidc-role-arn:
aws-oicd-role-arn:
description: 'OIDC role arn to interract with S3'
required: true
@@ -66,7 +66,7 @@ runs:
with:
name: neon-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build_type }}${{ inputs.sanitizers == 'enabled' && '-sanitized' || '' }}-artifact
path: /tmp/neon
aws-oidc-role-arn: ${{ inputs.aws-oidc-role-arn }}
aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}
- name: Download Neon binaries for the previous release
if: inputs.build_type != 'remote'
@@ -75,7 +75,7 @@ runs:
name: neon-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build_type }}-artifact
path: /tmp/neon-previous
prefix: latest
aws-oidc-role-arn: ${{ inputs.aws-oidc-role-arn }}
aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}
- name: Download compatibility snapshot
if: inputs.build_type != 'remote'
@@ -87,7 +87,7 @@ runs:
# The lack of compatibility snapshot (for example, for the new Postgres version)
# shouldn't fail the whole job. Only relevant test should fail.
skip-if-does-not-exist: true
aws-oidc-role-arn: ${{ inputs.aws-oidc-role-arn }}
aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}
- name: Checkout
if: inputs.needs_postgres_source == 'true'
@@ -228,13 +228,13 @@ runs:
# The lack of compatibility snapshot shouldn't fail the job
# (for example if we didn't run the test for non build-and-test workflow)
skip-if-does-not-exist: true
aws-oidc-role-arn: ${{ inputs.aws-oidc-role-arn }}
aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}
- uses: aws-actions/configure-aws-credentials@v4
if: ${{ !cancelled() }}
with:
aws-region: eu-central-1
role-to-assume: ${{ inputs.aws-oidc-role-arn }}
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
@@ -243,4 +243,4 @@ runs:
with:
report-dir: /tmp/test_output/allure/results
unique-key: ${{ inputs.build_type }}-${{ inputs.pg_version }}-${{ runner.arch }}
aws-oidc-role-arn: ${{ inputs.aws-oidc-role-arn }}
aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}

View File

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

View File

@@ -14,7 +14,7 @@ inputs:
prefix:
description: "S3 prefix. Default is '${GITHUB_SHA}/${GITHUB_RUN_ID}/${GITHUB_RUN_ATTEMPT}'"
required: false
aws-oidc-role-arn:
aws-oicd-role-arn:
description: "the OIDC role arn for aws auth"
required: false
default: ""
@@ -61,7 +61,7 @@ runs:
uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: eu-central-1
role-to-assume: ${{ inputs.aws-oidc-role-arn }}
role-to-assume: ${{ inputs.aws-oicd-role-arn }}
role-duration-seconds: 3600
- name: Upload artifact

View File

@@ -41,7 +41,7 @@ echo "Merge base of ${MAIN_BRANCH} and ${RELEASE_BRANCH}: ${MERGE_BASE}"
LAST_COMMIT=$(git rev-parse HEAD)
MERGE_COMMIT_MESSAGE=$(git log -1 --format=%s "${LAST_COMMIT}")
EXPECTED_MESSAGE_REGEX="^$COMPONENT release [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2} UTC$"
EXPECTED_MESSAGE_REGEX="^$COMPONENT release [0-9]{4}-[0-9]{2}-[0-9]{2}$"
if ! [[ "${MERGE_COMMIT_MESSAGE}" =~ ${EXPECTED_MESSAGE_REGEX} ]]; then
report_error "Merge commit message does not match expected pattern: '<component> release YYYY-MM-DD'

View File

@@ -81,7 +81,7 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
# we create a table that has one row for each database that we want to restore with the status whether the restore is done
- name: Create benchmark_restore_status table if it does not exist

View File

@@ -28,21 +28,6 @@ on:
required: false
default: 'disabled'
type: string
test-selection:
description: 'specification of selected test(s) to run'
required: false
default: ''
type: string
test-run-count:
description: 'number of runs to perform for selected tests'
required: false
default: 1
type: number
rerun-failed:
description: 'rerun failed tests to ignore flaky tests'
required: false
default: true
type: boolean
defaults:
run:
@@ -104,10 +89,11 @@ jobs:
# Set some environment variables used by all the steps.
#
# CARGO_FLAGS is extra options to pass to all "cargo" subcommands.
# CARGO_FLAGS is extra options to pass to "cargo build", "cargo test" etc.
# It also includes --features, if any
#
# CARGO_PROFILE is passed to "cargo build", "cargo test" etc, but not to
# "cargo metadata", because it doesn't accept --release or --debug options.
# CARGO_FEATURES is passed to "cargo metadata". It is separate from CARGO_FLAGS,
# because "cargo metadata" doesn't accept --release or --debug options
#
# We run tests with addtional features, that are turned off by default (e.g. in release builds), see
# corresponding Cargo.toml files for their descriptions.
@@ -116,16 +102,16 @@ jobs:
ARCH: ${{ inputs.arch }}
SANITIZERS: ${{ inputs.sanitizers }}
run: |
CARGO_FLAGS="--locked --features testing"
CARGO_FEATURES="--features testing"
if [[ $BUILD_TYPE == "debug" && $ARCH == 'x64' ]]; then
cov_prefix="scripts/coverage --profraw-prefix=$GITHUB_JOB --dir=/tmp/coverage run"
CARGO_PROFILE=""
CARGO_FLAGS="--locked"
elif [[ $BUILD_TYPE == "debug" ]]; then
cov_prefix=""
CARGO_PROFILE=""
CARGO_FLAGS="--locked"
elif [[ $BUILD_TYPE == "release" ]]; then
cov_prefix=""
CARGO_PROFILE="--release"
CARGO_FLAGS="--locked --release"
fi
if [[ $SANITIZERS == 'enabled' ]]; then
make_vars="WITH_SANITIZERS=yes"
@@ -135,8 +121,8 @@ jobs:
{
echo "cov_prefix=${cov_prefix}"
echo "make_vars=${make_vars}"
echo "CARGO_FEATURES=${CARGO_FEATURES}"
echo "CARGO_FLAGS=${CARGO_FLAGS}"
echo "CARGO_PROFILE=${CARGO_PROFILE}"
echo "CARGO_HOME=${GITHUB_WORKSPACE}/.cargo"
} >> $GITHUB_ENV
@@ -188,18 +174,34 @@ jobs:
path: pg_install/v17
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v17_rev.outputs.pg_rev }}-bookworm-${{ hashFiles('Makefile', 'build-tools.Dockerfile') }}
- name: Build all
# Note: the Makefile picks up BUILD_TYPE and CARGO_PROFILE from the env variables
run: mold -run make ${make_vars} all -j$(nproc) CARGO_BUILD_FLAGS="$CARGO_FLAGS"
- name: Build postgres v14
if: steps.cache_pg_14.outputs.cache-hit != 'true'
run: mold -run make ${make_vars} postgres-v14 -j$(nproc)
- name: Build postgres v15
if: steps.cache_pg_15.outputs.cache-hit != 'true'
run: mold -run make ${make_vars} postgres-v15 -j$(nproc)
- name: Build postgres v16
if: steps.cache_pg_16.outputs.cache-hit != 'true'
run: mold -run make ${make_vars} postgres-v16 -j$(nproc)
- name: Build postgres v17
if: steps.cache_pg_17.outputs.cache-hit != 'true'
run: mold -run make ${make_vars} postgres-v17 -j$(nproc)
- name: Build neon extensions
run: mold -run make ${make_vars} neon-pg-ext -j$(nproc)
- name: Build walproposer-lib
run: mold -run make ${make_vars} walproposer-lib -j$(nproc)
- name: Build unit tests
if: inputs.sanitizers != 'enabled'
- name: Run cargo build
env:
WITH_TESTS: ${{ inputs.sanitizers != 'enabled' && '--tests' || '' }}
run: |
export ASAN_OPTIONS=detect_leaks=0
${cov_prefix} mold -run cargo build $CARGO_FLAGS $CARGO_PROFILE --tests
${cov_prefix} mold -run cargo build $CARGO_FLAGS $CARGO_FEATURES --bins ${WITH_TESTS}
# Do install *before* running rust tests because they might recompile the
# binaries with different features/flags.
@@ -211,7 +213,7 @@ jobs:
# Install target binaries
mkdir -p /tmp/neon/bin/
binaries=$(
${cov_prefix} cargo metadata $CARGO_FLAGS --format-version=1 --no-deps |
${cov_prefix} cargo metadata $CARGO_FEATURES --format-version=1 --no-deps |
jq -r '.packages[].targets[] | select(.kind | index("bin")) | .name'
)
for bin in $binaries; do
@@ -228,7 +230,7 @@ jobs:
mkdir -p /tmp/neon/test_bin/
test_exe_paths=$(
${cov_prefix} cargo test $CARGO_FLAGS $CARGO_PROFILE --message-format=json --no-run |
${cov_prefix} cargo test $CARGO_FLAGS $CARGO_FEATURES --message-format=json --no-run |
jq -r '.executable | select(. != null)'
)
for bin in $test_exe_paths; do
@@ -262,25 +264,29 @@ jobs:
export LD_LIBRARY_PATH
#nextest does not yet support running doctests
${cov_prefix} cargo test --doc $CARGO_FLAGS $CARGO_PROFILE
${cov_prefix} cargo test --doc $CARGO_FLAGS $CARGO_FEATURES
# run all non-pageserver tests
${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_PROFILE -E '!package(pageserver)'
${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_FEATURES -E '!package(pageserver)'
# run pageserver tests
# (When developing new pageserver features gated by config fields, we commonly make the rust
# unit tests sensitive to an environment variable NEON_PAGESERVER_UNIT_TEST_FEATURENAME.
# Then run the nextest invocation below for all relevant combinations. Singling out the
# pageserver tests from non-pageserver tests cuts down the time it takes for this CI step.)
NEON_PAGESERVER_UNIT_TEST_VIRTUAL_FILE_IOENGINE=tokio-epoll-uring \
${cov_prefix} \
cargo nextest run $CARGO_FLAGS $CARGO_PROFILE -E 'package(pageserver)'
# run pageserver tests with different settings
for get_vectored_concurrent_io in sequential sidecar-task; do
for io_engine in std-fs tokio-epoll-uring ; do
for io_mode in buffered direct direct-rw ; do
NEON_PAGESERVER_UNIT_TEST_GET_VECTORED_CONCURRENT_IO=$get_vectored_concurrent_io \
NEON_PAGESERVER_UNIT_TEST_VIRTUAL_FILE_IOENGINE=$io_engine \
NEON_PAGESERVER_UNIT_TEST_VIRTUAL_FILE_IO_MODE=$io_mode \
${cov_prefix} \
cargo nextest run $CARGO_FLAGS $CARGO_FEATURES -E 'package(pageserver)'
done
done
done
# Run separate tests for real S3
export ENABLE_REAL_S3_REMOTE_STORAGE=nonempty
export REMOTE_STORAGE_S3_BUCKET=neon-github-ci-tests
export REMOTE_STORAGE_S3_REGION=eu-central-1
${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_PROFILE -E 'package(remote_storage)' -E 'test(test_real_s3)'
${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_FEATURES -E 'package(remote_storage)' -E 'test(test_real_s3)'
# Run separate tests for real Azure Blob Storage
# XXX: replace region with `eu-central-1`-like region
@@ -289,17 +295,17 @@ jobs:
export AZURE_STORAGE_ACCESS_KEY="${{ secrets.AZURE_STORAGE_ACCESS_KEY_DEV }}"
export REMOTE_STORAGE_AZURE_CONTAINER="${{ vars.REMOTE_STORAGE_AZURE_CONTAINER }}"
export REMOTE_STORAGE_AZURE_REGION="${{ vars.REMOTE_STORAGE_AZURE_REGION }}"
${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_PROFILE -E 'package(remote_storage)' -E 'test(test_real_azure)'
${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_FEATURES -E 'package(remote_storage)' -E 'test(test_real_azure)'
- name: Install postgres binaries
run: |
# Use tar to copy files matching the pattern, preserving the paths in the destionation
tar c \
pg_install/v* \
build/*/src/test/regress/*.so \
build/*/src/test/regress/pg_regress \
build/*/src/test/isolation/isolationtester \
build/*/src/test/isolation/pg_isolation_regress \
pg_install/build/*/src/test/regress/*.so \
pg_install/build/*/src/test/regress/pg_regress \
pg_install/build/*/src/test/isolation/isolationtester \
pg_install/build/*/src/test/isolation/pg_isolation_regress \
| tar x -C /tmp/neon
- name: Upload Neon artifact
@@ -307,7 +313,7 @@ jobs:
with:
name: neon-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}${{ inputs.sanitizers == 'enabled' && '-sanitized' || '' }}-artifact
path: /tmp/neon
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Check diesel schema
if: inputs.build-type == 'release' && inputs.arch == 'x64'
@@ -367,7 +373,7 @@ jobs:
- name: Pytest regression tests
continue-on-error: ${{ matrix.lfc_state == 'with-lfc' && inputs.build-type == 'debug' }}
uses: ./.github/actions/run-python-test-set
timeout-minutes: ${{ (inputs.build-type == 'release' && inputs.sanitizers != 'enabled') && 75 || 180 }}
timeout-minutes: ${{ inputs.sanitizers != 'enabled' && 75 || 180 }}
with:
build_type: ${{ inputs.build-type }}
test_selection: regress
@@ -375,20 +381,21 @@ jobs:
run_with_real_s3: true
real_s3_bucket: neon-github-ci-tests
real_s3_region: eu-central-1
rerun_failed: ${{ inputs.rerun-failed }}
rerun_failed: true
pg_version: ${{ matrix.pg_version }}
sanitizers: ${{ inputs.sanitizers }}
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
# `--session-timeout` is equal to (timeout-minutes - 10 minutes) * 60 seconds.
# Attempt to stop tests gracefully to generate test reports
# until they are forcibly stopped by the stricter `timeout-minutes` limit.
extra_params: --session-timeout=${{ (inputs.build-type == 'release' && inputs.sanitizers != 'enabled') && 3000 || 10200 }} --count=${{ inputs.test-run-count }}
${{ inputs.test-selection != '' && format('-k "{0}"', inputs.test-selection) || '' }}
extra_params: --session-timeout=${{ inputs.sanitizers != 'enabled' && 3000 || 10200 }}
env:
TEST_RESULT_CONNSTR: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
CHECK_ONDISK_DATA_COMPATIBILITY: nonempty
BUILD_TAG: ${{ inputs.build-tag }}
PAGESERVER_VIRTUAL_FILE_IO_ENGINE: tokio-epoll-uring
PAGESERVER_GET_VECTORED_CONCURRENT_IO: sidecar-task
PAGESERVER_VIRTUAL_FILE_IO_MODE: direct-rw
USE_LFC: ${{ matrix.lfc_state == 'with-lfc' && 'true' || 'false' }}
# Temporary disable this step until we figure out why it's so flaky

103
.github/workflows/_create-release-pr.yml vendored Normal file
View File

@@ -0,0 +1,103 @@
name: Create Release PR
on:
workflow_call:
inputs:
component-name:
description: 'Component name'
required: true
type: string
source-branch:
description: 'Source branch'
required: true
type: string
secrets:
ci-access-token:
description: 'CI access token'
required: true
defaults:
run:
shell: bash -euo pipefail {0}
permissions:
contents: read
jobs:
create-release-branch:
runs-on: ubuntu-22.04
permissions:
contents: write # for `git push`
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
ref: ${{ inputs.source-branch }}
fetch-depth: 0
- name: Set variables
id: vars
env:
COMPONENT_NAME: ${{ inputs.component-name }}
RELEASE_BRANCH: >-
${{
false
|| inputs.component-name == 'Storage' && 'release'
|| inputs.component-name == 'Proxy' && 'release-proxy'
|| inputs.component-name == 'Compute' && 'release-compute'
}}
run: |
now_date=$(date -u +'%Y-%m-%d')
now_time=$(date -u +'%H-%M-%Z')
{
echo "title=${COMPONENT_NAME} release ${now_date}"
echo "rc-branch=rc/${RELEASE_BRANCH}/${now_date}_${now_time}"
echo "release-branch=${RELEASE_BRANCH}"
} | 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:
RELEASE_BRANCH: ${{ steps.vars.outputs.release-branch }}
RC_BRANCH: ${{ steps.vars.outputs.rc-branch }}
TITLE: ${{ steps.vars.outputs.title }}
run: |
git switch -c "${RC_BRANCH}"
# Manually create a merge commit on the current branch, keeping the
# tree and setting the parents to the current HEAD and the HEAD of the
# release branch. This commit is what we'll fast-forward the release
# branch to when merging the release branch.
# For details on why, look at
# https://docs.neon.build/overview/repositories/neon.html#background-on-commit-history-of-release-prs
current_tree=$(git rev-parse 'HEAD^{tree}')
release_head=$(git rev-parse "origin/${RELEASE_BRANCH}")
current_head=$(git rev-parse HEAD)
merge_commit=$(git commit-tree -p "${current_head}" -p "${release_head}" -m "${TITLE}" "${current_tree}")
# Fast-forward the current branch to the newly created merge_commit
git merge --ff-only ${merge_commit}
git push origin "${RC_BRANCH}"
- name: Create a PR into ${{ steps.vars.outputs.release-branch }}
env:
GH_TOKEN: ${{ secrets.ci-access-token }}
RC_BRANCH: ${{ steps.vars.outputs.rc-branch }}
RELEASE_BRANCH: ${{ steps.vars.outputs.release-branch }}
TITLE: ${{ steps.vars.outputs.title }}
run: |
gh pr create --title "${TITLE}" \
--body "" \
--head "${RC_BRANCH}" \
--base "${RELEASE_BRANCH}"

View File

@@ -53,77 +53,6 @@ concurrency:
cancel-in-progress: true
jobs:
cleanup:
runs-on: [ self-hosted, us-east-2, x64 ]
container:
image: ghcr.io/neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
env:
ORG_ID: org-solitary-dew-09443886
LIMIT: 100
SEARCH: "GITHUB_RUN_ID="
BASE_URL: https://console-stage.neon.build/api/v2
DRY_RUN: "false" # Set to "true" to just test out the workflow
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Cleanup inactive Neon projects left over from prior runs
env:
API_KEY: ${{ secrets.NEON_STAGING_API_KEY }}
run: |
set -euo pipefail
NOW=$(date -u +%s)
DAYS_AGO=$((NOW - 5 * 86400))
REQUEST_URL="$BASE_URL/projects?limit=$LIMIT&search=$(printf '%s' "$SEARCH" | jq -sRr @uri)&org_id=$ORG_ID"
echo "Requesting project list from:"
echo "$REQUEST_URL"
response=$(curl -s -X GET "$REQUEST_URL" \
--header "Accept: application/json" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${API_KEY}" )
echo "Response:"
echo "$response" | jq .
projects_to_delete=$(echo "$response" | jq --argjson cutoff "$DAYS_AGO" '
.projects[]
| select(.compute_last_active_at != null)
| select((.compute_last_active_at | fromdateiso8601) < $cutoff)
| {id, name, compute_last_active_at}
')
if [ -z "$projects_to_delete" ]; then
echo "No projects eligible for deletion."
exit 0
fi
echo "Projects that will be deleted:"
echo "$projects_to_delete" | jq -r '.id'
if [ "$DRY_RUN" = "false" ]; then
echo "$projects_to_delete" | jq -r '.id' | while read -r project_id; do
echo "Deleting project: $project_id"
curl -s -X DELETE "$BASE_URL/projects/$project_id" \
--header "Accept: application/json" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${API_KEY}"
done
else
echo "Dry run enabled — no projects were deleted."
fi
bench:
if: ${{ github.event.inputs.run_only_pgvector_tests == 'false' || github.event.inputs.run_only_pgvector_tests == null }}
permissions:
@@ -185,7 +114,7 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Create Neon Project
id: create-neon-project
@@ -203,7 +132,7 @@ jobs:
run_in_parallel: false
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
pg_version: ${{ env.PG_VERSION }}
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
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
@@ -236,7 +165,7 @@ jobs:
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
with:
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
@@ -293,8 +222,8 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Verify that cumulative statistics are preserved
uses: ./.github/actions/run-python-test-set
with:
@@ -304,7 +233,7 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 3600
pg_version: ${{ env.DEFAULT_PG_VERSION }}
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
@@ -353,7 +282,7 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Run Logical Replication benchmarks
uses: ./.github/actions/run-python-test-set
@@ -364,7 +293,7 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 5400
pg_version: ${{ env.DEFAULT_PG_VERSION }}
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
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 }}"
@@ -381,7 +310,7 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 5400
pg_version: ${{ env.DEFAULT_PG_VERSION }}
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
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 }}"
@@ -393,7 +322,7 @@ jobs:
uses: ./.github/actions/allure-report-generate
with:
store-test-results-into-db: true
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
@@ -576,7 +505,7 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Create Neon Project
if: contains(fromJSON('["neonvm-captest-new", "neonvm-captest-new-many-tables", "neonvm-captest-freetier", "neonvm-azure-captest-freetier", "neonvm-azure-captest-new"]'), matrix.platform)
@@ -628,7 +557,7 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_perf_many_relations
pg_version: ${{ env.PG_VERSION }}
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
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 }}"
@@ -644,7 +573,7 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_init
pg_version: ${{ env.PG_VERSION }}
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
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 }}"
@@ -659,7 +588,7 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_simple_update
pg_version: ${{ env.PG_VERSION }}
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
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 }}"
@@ -674,7 +603,7 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_select_only
pg_version: ${{ env.PG_VERSION }}
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
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 }}"
@@ -692,7 +621,7 @@ jobs:
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
with:
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
@@ -765,7 +694,7 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Set up Connection String
id: set-up-connstr
@@ -797,7 +726,7 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_pgvector_indexing
pg_version: ${{ env.PG_VERSION }}
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
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 }}"
@@ -812,7 +741,7 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600
pg_version: ${{ env.PG_VERSION }}
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
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 }}"
@@ -823,7 +752,7 @@ jobs:
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
with:
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
@@ -899,7 +828,7 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Set up Connection String
id: set-up-connstr
@@ -942,7 +871,7 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 43200 -k test_clickbench
pg_version: ${{ env.PG_VERSION }}
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
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 }}"
@@ -956,7 +885,7 @@ jobs:
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
with:
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
@@ -1025,7 +954,7 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Get Connstring Secret Name
run: |
@@ -1074,7 +1003,7 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_tpch
pg_version: ${{ env.PG_VERSION }}
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
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 }}"
@@ -1086,7 +1015,7 @@ jobs:
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
with:
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
@@ -1149,7 +1078,7 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Set up Connection String
id: set-up-connstr
@@ -1192,7 +1121,7 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_user_examples
pg_version: ${{ env.PG_VERSION }}
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
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 }}"
@@ -1203,7 +1132,7 @@ jobs:
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
with:
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}

View File

@@ -34,10 +34,11 @@ permissions:
jobs:
build-pgxn:
if: |
inputs.pg_versions != '[]' || inputs.rebuild_everything ||
contains(github.event.pull_request.labels.*.name, 'run-extra-build-macos') ||
contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
github.ref_name == 'main'
(inputs.pg_versions != '[]' || inputs.rebuild_everything) && (
contains(github.event.pull_request.labels.*.name, 'run-extra-build-macos') ||
contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
github.ref_name == 'main'
)
timeout-minutes: 30
runs-on: macos-15
strategy:
@@ -94,21 +95,18 @@ jobs:
run: |
make "neon-pg-ext-${{ matrix.postgres-version }}" -j$(sysctl -n hw.ncpu)
- name: Upload "pg_install/${{ matrix.postgres-version }}" artifact
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
with:
name: pg_install--${{ matrix.postgres-version }}
path: pg_install/${{ matrix.postgres-version }}
# The artifact is supposed to be used by the next job in the same workflow,
# so theres no need to store it for too long.
retention-days: 1
- name: Get postgres headers ${{ matrix.postgres-version }}
if: steps.cache_pg.outputs.cache-hit != 'true'
run: |
make postgres-headers-${{ matrix.postgres-version }} -j$(sysctl -n hw.ncpu)
build-walproposer-lib:
if: |
contains(inputs.pg_versions, 'v17') || inputs.rebuild_everything ||
contains(github.event.pull_request.labels.*.name, 'run-extra-build-macos') ||
contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
github.ref_name == 'main'
(inputs.pg_versions != '[]' || inputs.rebuild_everything) && (
contains(github.event.pull_request.labels.*.name, 'run-extra-build-macos') ||
contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
github.ref_name == 'main'
)
timeout-minutes: 30
runs-on: macos-15
needs: [build-pgxn]
@@ -129,17 +127,18 @@ jobs:
id: pg_rev
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v17) | tee -a "${GITHUB_OUTPUT}"
- name: Download "pg_install/v17" artifact
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
- name: Cache postgres v17 build
id: cache_pg
uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
with:
name: pg_install--v17
path: pg_install/v17
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-v17-${{ steps.pg_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Cache walproposer-lib
id: cache_walproposer_lib
uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
with:
path: build/walproposer-lib
path: pg_install/build/walproposer-lib
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-walproposer_lib-v17-${{ steps.pg_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Checkout submodule vendor/postgres-v17
@@ -164,21 +163,13 @@ jobs:
run:
make walproposer-lib -j$(sysctl -n hw.ncpu)
- name: Upload "build/walproposer-lib" artifact
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
with:
name: build--walproposer-lib
path: build/walproposer-lib
# The artifact is supposed to be used by the next job in the same workflow,
# so theres no need to store it for too long.
retention-days: 1
cargo-build:
if: |
inputs.pg_versions != '[]' || inputs.rebuild_rust_code || inputs.rebuild_everything ||
contains(github.event.pull_request.labels.*.name, 'run-extra-build-macos') ||
contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
github.ref_name == 'main'
(inputs.pg_versions != '[]' || inputs.rebuild_rust_code || inputs.rebuild_everything) && (
contains(github.event.pull_request.labels.*.name, 'run-extra-build-macos') ||
contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
github.ref_name == 'main'
)
timeout-minutes: 30
runs-on: macos-15
needs: [build-pgxn, build-walproposer-lib]
@@ -197,43 +188,45 @@ jobs:
with:
submodules: true
- name: Download "pg_install/v14" artifact
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
- name: Set pg v14 for caching
id: pg_rev_v14
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v14) | tee -a "${GITHUB_OUTPUT}"
- name: Set pg v15 for caching
id: pg_rev_v15
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v15) | tee -a "${GITHUB_OUTPUT}"
- name: Set pg v16 for caching
id: pg_rev_v16
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v16) | tee -a "${GITHUB_OUTPUT}"
- name: Set pg v17 for caching
id: pg_rev_v17
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v17) | tee -a "${GITHUB_OUTPUT}"
- name: Cache postgres v14 build
id: cache_pg
uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
with:
name: pg_install--v14
path: pg_install/v14
- name: Download "pg_install/v15" artifact
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-v14-${{ steps.pg_rev_v14.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Cache postgres v15 build
id: cache_pg_v15
uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
with:
name: pg_install--v15
path: pg_install/v15
- name: Download "pg_install/v16" artifact
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-v15-${{ steps.pg_rev_v15.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Cache postgres v16 build
id: cache_pg_v16
uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
with:
name: pg_install--v16
path: pg_install/v16
- name: Download "pg_install/v17" artifact
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-v16-${{ steps.pg_rev_v16.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Cache postgres v17 build
id: cache_pg_v17
uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
with:
name: pg_install--v17
path: pg_install/v17
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-v17-${{ steps.pg_rev_v17.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Download "build/walproposer-lib" artifact
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
with:
name: build--walproposer-lib
path: build/walproposer-lib
# `actions/download-artifact` doesn't preserve permissions:
# https://github.com/actions/download-artifact?tab=readme-ov-file#permission-loss
- name: Make pg_install/v*/bin/* executable
run: |
chmod +x pg_install/v*/bin/*
- name: Cache cargo deps
- name: Cache cargo deps (only for v17)
uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
with:
path: |
@@ -243,6 +236,13 @@ jobs:
target
key: v1-${{ runner.os }}-${{ runner.arch }}-cargo-${{ hashFiles('./Cargo.lock') }}-${{ hashFiles('./rust-toolchain.toml') }}-rust
- name: Cache walproposer-lib
id: cache_walproposer_lib
uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
with:
path: pg_install/build/walproposer-lib
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-walproposer_lib-v17-${{ steps.pg_rev_v17.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Install build dependencies
run: |
brew install flex bison openssl protobuf icu4c
@@ -252,8 +252,8 @@ jobs:
echo 'LDFLAGS=-L/usr/local/opt/openssl@3/lib' >> $GITHUB_ENV
echo 'CPPFLAGS=-I/usr/local/opt/openssl@3/include' >> $GITHUB_ENV
- name: Run cargo build
- name: Run cargo build (only for v17)
run: cargo build --all --release -j$(sysctl -n hw.ncpu)
- name: Check that no warnings are produced
- name: Check that no warnings are produced (only for v17)
run: ./run_clippy.sh

View File

@@ -1,121 +0,0 @@
name: Build and Run Selected Test
on:
workflow_dispatch:
inputs:
test-selection:
description: 'Specification of selected test(s), as accepted by pytest -k'
required: true
type: string
run-count:
description: 'Number of test runs to perform'
required: true
type: number
archs:
description: 'Archs to run tests on, e. g.: ["x64", "arm64"]'
default: '["x64"]'
required: true
type: string
build-types:
description: 'Build types to run tests on, e. g.: ["debug", "release"]'
default: '["release"]'
required: true
type: string
pg-versions:
description: 'Postgres versions to use for testing, e.g,: [{"pg_version":"v16"}, {"pg_version":"v17"}])'
default: '[{"pg_version":"v17"}]'
required: true
type: string
defaults:
run:
shell: bash -euxo pipefail {0}
env:
RUST_BACKTRACE: 1
COPT: '-Werror'
jobs:
meta:
uses: ./.github/workflows/_meta.yml
with:
github-event-name: ${{ github.event_name }}
github-event-json: ${{ toJSON(github.event) }}
build-and-test-locally:
needs: [ meta ]
strategy:
fail-fast: false
matrix:
arch: ${{ fromJson(inputs.archs) }}
build-type: ${{ fromJson(inputs.build-types) }}
uses: ./.github/workflows/_build-and-test-locally.yml
with:
arch: ${{ matrix.arch }}
build-tools-image: ghcr.io/neondatabase/build-tools:pinned-bookworm
build-tag: ${{ needs.meta.outputs.build-tag }}
build-type: ${{ matrix.build-type }}
test-cfg: ${{ inputs.pg-versions }}
test-selection: ${{ inputs.test-selection }}
test-run-count: ${{ fromJson(inputs.run-count) }}
rerun-failed: false
secrets: inherit
create-test-report:
needs: [ build-and-test-locally ]
if: ${{ !cancelled() }}
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: write
pull-requests: write
outputs:
report-url: ${{ steps.create-allure-report.outputs.report-url }}
runs-on: [ self-hosted, small ]
container:
image: ghcr.io/neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Create Allure report
if: ${{ !cancelled() }}
id: create-allure-report
uses: ./.github/actions/allure-report-generate
with:
store-test-results-into-db: true
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_DEV }}
- uses: actions/github-script@v7
if: ${{ !cancelled() }}
with:
# Retry script for 5XX server errors: https://github.com/actions/github-script#retries
retries: 5
script: |
const report = {
reportUrl: "${{ steps.create-allure-report.outputs.report-url }}",
reportJsonUrl: "${{ steps.create-allure-report.outputs.report-json-url }}",
}
const coverage = {}
const script = require("./scripts/comment-test-report.js")
await script({
github,
context,
fetch,
report,
coverage,
})

View File

@@ -69,7 +69,7 @@ jobs:
submodules: true
- name: Check for file changes
uses: step-security/paths-filter@v3
uses: dorny/paths-filter@de90cc6fb38fc0963ad72b210f1f284cd68cea36 # v3.0.2
id: files-changed
with:
token: ${{ secrets.GITHUB_TOKEN }}
@@ -199,28 +199,6 @@ jobs:
build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
secrets: inherit
validate-compute-manifest:
runs-on: ubuntu-22.04
needs: [ meta, check-permissions ]
# We do need to run this in `.*-rc-pr` because of hotfixes.
if: ${{ contains(fromJSON('["pr", "push-main", "storage-rc-pr", "proxy-rc-pr", "compute-rc-pr"]'), needs.meta.outputs.run-kind) }}
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Set up Node.js
uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4.4.0
with:
node-version: '24'
- name: Validate manifest against schema
run: |
make -C compute manifest-schema-validation
build-and-test-locally:
needs: [ meta, build-build-tools-image ]
# We do need to run this in `.*-rc-pr` because of hotfixes.
@@ -336,16 +314,17 @@ jobs:
test_selection: performance
run_in_parallel: false
save_perf_report: ${{ github.ref_name == 'main' }}
# test_pageserver_max_throughput_getpage_at_latest_lsn is run in separate workflow periodic_pagebench.yml because it needs snapshots
extra_params: --splits 5 --group ${{ matrix.pytest_split_group }} --ignore=test_runner/performance/pageserver/pagebench/test_pageserver_max_throughput_getpage_at_latest_lsn.py
extra_params: --splits 5 --group ${{ matrix.pytest_split_group }}
benchmark_durations: ${{ needs.get-benchmarks-durations.outputs.json }}
pg_version: v16
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
TEST_RESULT_CONNSTR: "${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}"
PAGESERVER_VIRTUAL_FILE_IO_ENGINE: tokio-epoll-uring
PAGESERVER_GET_VECTORED_CONCURRENT_IO: sidecar-task
PAGESERVER_VIRTUAL_FILE_IO_MODE: direct-rw
SYNC_BETWEEN_TESTS: true
# XXX: no coverage data handling here, since benchmarks are run on release builds,
# while coverage is currently collected for the debug ones
@@ -405,7 +384,7 @@ jobs:
uses: ./.github/actions/allure-report-generate
with:
store-test-results-into-db: true
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
@@ -472,14 +451,14 @@ jobs:
with:
name: neon-${{ runner.os }}-${{ runner.arch }}-${{ matrix.build_type }}-artifact
path: /tmp/neon
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Get coverage artifact
uses: ./.github/actions/download
with:
name: coverage-data-artifact
path: /tmp/coverage
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Merge coverage data
run: scripts/coverage "--profraw-prefix=$GITHUB_JOB" --dir=/tmp/coverage merge
@@ -670,7 +649,7 @@ jobs:
ghcr.io/neondatabase/neon:${{ needs.meta.outputs.build-tag }}-bookworm-arm64
compute-node-image-arch:
needs: [ check-permissions, meta ]
needs: [ check-permissions, build-build-tools-image, meta ]
if: ${{ contains(fromJSON('["push-main", "pr", "compute-rc-pr"]'), needs.meta.outputs.run-kind) }}
permissions:
id-token: write # aws-actions/configure-aws-credentials
@@ -743,6 +722,7 @@ jobs:
GIT_VERSION=${{ github.event.pull_request.head.sha || github.sha }}
PG_VERSION=${{ matrix.version.pg }}
BUILD_TAG=${{ needs.meta.outputs.release-tag || needs.meta.outputs.build-tag }}
TAG=${{ needs.build-build-tools-image.outputs.image-tag }}-${{ matrix.version.debian }}
DEBIAN_VERSION=${{ matrix.version.debian }}
provenance: false
push: true
@@ -762,6 +742,7 @@ jobs:
GIT_VERSION=${{ github.event.pull_request.head.sha || github.sha }}
PG_VERSION=${{ matrix.version.pg }}
BUILD_TAG=${{ needs.meta.outputs.release-tag || needs.meta.outputs.build-tag }}
TAG=${{ needs.build-build-tools-image.outputs.image-tag }}-${{ matrix.version.debian }}
DEBIAN_VERSION=${{ matrix.version.debian }}
provenance: false
push: true
@@ -843,7 +824,7 @@ jobs:
- pg: v17
debian: bookworm
env:
VM_BUILDER_VERSION: v0.46.0
VM_BUILDER_VERSION: v0.42.2
steps:
- name: Harden the runner (Audit all outbound calls)
@@ -984,7 +965,7 @@ jobs:
fi
- name: Verify docker-compose example and test extensions
timeout-minutes: 60
timeout-minutes: 20
env:
TAG: >-
${{
@@ -1453,10 +1434,10 @@ jobs:
;;
esac
notify-release-deploy-failure:
needs: [ meta, deploy ]
notify-storage-release-deploy-failure:
needs: [ deploy ]
# We want this to run even if (transitive) dependencies are skipped, because deploy should really be successful on release branch workflow runs.
if: contains(fromJSON('["storage-release", "compute-release", "proxy-release"]'), needs.meta.outputs.run-kind) && needs.deploy.result != 'success' && always()
if: github.ref_name == 'release' && needs.deploy.result != 'success' && always()
runs-on: ubuntu-22.04
steps:
- name: Harden the runner (Audit all outbound calls)
@@ -1464,40 +1445,15 @@ jobs:
with:
egress-policy: audit
- name: Post release-deploy failure to team slack channel
- name: Post release-deploy failure to team-storage slack channel
uses: slackapi/slack-github-action@485a9d42d3a73031f12ec201c457e2162c45d02d # v2.0.0
env:
TEAM_ONCALL: >-
${{
fromJSON(format('{
"storage-release": "<!subteam^{0}|@oncall-storage>",
"compute-release": "<!subteam^{1}|@oncall-compute>",
"proxy-release": "<!subteam^{2}|@oncall-proxy>"
}',
vars.SLACK_ONCALL_STORAGE_GROUP,
vars.SLACK_ONCALL_COMPUTE_GROUP,
vars.SLACK_ONCALL_PROXY_GROUP
))[needs.meta.outputs.run-kind]
}}
CHANNEL: >-
${{
fromJSON(format('{
"storage-release": "{0}",
"compute-release": "{1}",
"proxy-release": "{2}"
}',
vars.SLACK_STORAGE_CHANNEL_ID,
vars.SLACK_COMPUTE_CHANNEL_ID,
vars.SLACK_PROXY_CHANNEL_ID
))[needs.meta.outputs.run-kind]
}}
with:
method: chat.postMessage
token: ${{ secrets.SLACK_BOT_TOKEN }}
payload: |
channel: ${{ env.CHANNEL }}
channel: ${{ vars.SLACK_STORAGE_CHANNEL_ID }}
text: |
🔴 ${{ env.TEAM_ONCALL }}: deploy job on release branch had unexpected status "${{ needs.deploy.result }}" <${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}|GitHub Run>.
🔴 <!subteam^S06CJ87UMNY|@oncall-storage>: deploy job on release branch had unexpected status "${{ needs.deploy.result }}" <${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}|GitHub Run>.
# The job runs on `release` branch and copies compatibility data and Neon artifact from the last *release PR* to the latest directory
promote-compatibility-data:

View File

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

View File

@@ -79,7 +79,6 @@ jobs:
build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
build-tag: ${{ needs.tag.outputs.build-tag }}
build-type: ${{ matrix.build-type }}
rerun-failed: false
test-cfg: '[{"pg_version":"v17"}]'
sanitizers: enabled
secrets: inherit
@@ -118,7 +117,7 @@ jobs:
uses: ./.github/actions/allure-report-generate
with:
store-test-results-into-db: true
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}

View File

@@ -19,7 +19,7 @@ jobs:
runs-on: ubuntu-22.04
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@0634a2670c59f64b4a01f0f96f84700a4088b9f0 # v2.12.0
uses: step-security/harden-runner@v2
with:
egress-policy: audit

View File

@@ -12,7 +12,7 @@ jobs:
runs-on: ubuntu-22.04
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@0634a2670c59f64b4a01f0f96f84700a4088b9f0 # v2.12.0
uses: step-security/harden-runner@v2
with:
egress-policy: audit

View File

@@ -1,99 +0,0 @@
name: Cloud Extensions Test
on:
schedule:
# * is a special character in YAML so you have to quote this string
# ┌───────────── minute (0 - 59)
# │ ┌───────────── hour (0 - 23)
# │ │ ┌───────────── day of the month (1 - 31)
# │ │ │ ┌───────────── month (1 - 12 or JAN-DEC)
# │ │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
- cron: '45 1 * * *' # run once a day, timezone is utc
workflow_dispatch: # adds ability to run this manually
inputs:
region_id:
description: 'Project region id. If not set, the default region will be used'
required: false
default: 'aws-us-east-2'
defaults:
run:
shell: bash -euxo pipefail {0}
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: write
jobs:
regress:
env:
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
TEST_OUTPUT: /tmp/test_output
BUILD_TYPE: remote
strategy:
fail-fast: false
matrix:
pg-version: [16, 17]
runs-on: us-east-2
container:
# We use the neon-test-extensions image here as it contains the source code for the extensions.
image: ghcr.io/neondatabase/neon-test-extensions-v${{ matrix.pg-version }}:latest
credentials:
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Evaluate the settings
id: project-settings
run: |
if [[ $((${{ matrix.pg-version }})) -lt 17 ]]; then
ULID=ulid
else
ULID=pgx_ulid
fi
LIBS=timescaledb:rag_bge_small_en_v15,rag_jina_reranker_v1_tiny_en:$ULID
settings=$(jq -c -n --arg libs $LIBS '{preload_libraries:{use_defaults:false,enabled_libraries:($libs| split(":"))}}')
echo settings=$settings >> $GITHUB_OUTPUT
- name: Create Neon Project
id: create-neon-project
uses: ./.github/actions/neon-project-create
with:
region_id: ${{ inputs.region_id || 'aws-us-east-2' }}
postgres_version: ${{ matrix.pg-version }}
project_settings: ${{ steps.project-settings.outputs.settings }}
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
- name: Run the regression tests
run: /run-tests.sh -r /ext-src
env:
BENCHMARK_CONNSTR: ${{ steps.create-neon-project.outputs.dsn }}
SKIP: "pg_hint_plan-src,pg_repack-src,pg_cron-src,plpgsql_check-src"
- name: Delete Neon Project
if: ${{ always() }}
uses: ./.github/actions/neon-project-delete
with:
project_id: ${{ steps.create-neon-project.outputs.project_id }}
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@fcfb566f8b0aab22203f066d80ca1d7e4b5d05b3 # v1.27.1
with:
channel-id: ${{ vars.SLACK_ON_CALL_QA_STAGING_STREAM }}
slack-message: |
Periodic extensions test on staging: ${{ job.status }}
<${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}|GitHub Run>
env:
SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}

View File

@@ -89,7 +89,7 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Create a new branch
id: create-branch
@@ -105,7 +105,7 @@ jobs:
test_selection: cloud_regress
pg_version: ${{matrix.pg-version}}
extra_params: -m remote_cluster
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
BENCHMARK_CONNSTR: ${{steps.create-branch.outputs.dsn}}
@@ -122,7 +122,7 @@ jobs:
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
with:
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}

View File

@@ -14,7 +14,7 @@ jobs:
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@0634a2670c59f64b4a01f0f96f84700a4088b9f0 # v2.12.0
uses: step-security/harden-runner@v2
with:
egress-policy: audit

View File

@@ -32,7 +32,7 @@ jobs:
fail-fast: false # allow other variants to continue even if one fails
matrix:
include:
- target_project: new_empty_project_stripe_size_2048
- target_project: new_empty_project_stripe_size_2048
stripe_size: 2048 # 16 MiB
postgres_version: 16
disable_sharding: false
@@ -98,7 +98,7 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Create Neon Project
if: ${{ startsWith(matrix.target_project, 'new_empty_project') }}
@@ -110,10 +110,10 @@ jobs:
compute_units: '[7, 7]' # we want to test large compute here to avoid compute-side bottleneck
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
shard_split_project: ${{ matrix.stripe_size != null && 'true' || 'false' }}
admin_api_key: ${{ secrets.NEON_STAGING_ADMIN_API_KEY }}
admin_api_key: ${{ secrets.NEON_STAGING_ADMIN_API_KEY }}
shard_count: 8
stripe_size: ${{ matrix.stripe_size }}
disable_sharding: ${{ matrix.disable_sharding }}
disable_sharding: ${{ matrix.disable_sharding }}
- name: Initialize Neon project
if: ${{ startsWith(matrix.target_project, 'new_empty_project') }}
@@ -171,7 +171,7 @@ jobs:
extra_params: -s -m remote_cluster --timeout 86400 -k test_ingest_performance_using_pgcopydb
pg_version: v${{ matrix.postgres_version }}
save_perf_report: true
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
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 }}

View File

@@ -28,7 +28,7 @@ jobs:
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@0634a2670c59f64b4a01f0f96f84700a4088b9f0 # v2.12.0
uses: step-security/harden-runner@v2
with:
egress-policy: audit
@@ -75,7 +75,7 @@ jobs:
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@0634a2670c59f64b4a01f0f96f84700a4088b9f0 # v2.12.0
uses: step-security/harden-runner@v2
with:
egress-policy: audit

View File

@@ -33,25 +33,17 @@ jobs:
fail-fast: false # allow other variants to continue even if one fails
matrix:
include:
# test only read-only custom scripts in new branch without database maintenance
- target: new_branch
custom_scripts: select_any_webhook_with_skew.sql@300 select_recent_webhook.sql@397 select_prefetch_webhook.sql@3
test_maintenance: false
# test all custom scripts in new branch with database maintenance
- target: new_branch
- target: new_branch
custom_scripts: insert_webhooks.sql@200 select_any_webhook_with_skew.sql@300 select_recent_webhook.sql@397 select_prefetch_webhook.sql@3 IUD_one_transaction.sql@100
test_maintenance: true
# test all custom scripts in reuse branch with database maintenance
- target: reuse_branch
- target: reuse_branch
custom_scripts: insert_webhooks.sql@200 select_any_webhook_with_skew.sql@300 select_recent_webhook.sql@397 select_prefetch_webhook.sql@3 IUD_one_transaction.sql@100
test_maintenance: true
max-parallel: 1 # we want to run each benchmark sequentially to not have noisy neighbors on shared storage (PS, SK)
max-parallel: 1 # we want to run each stripe size sequentially to be able to compare the results
permissions:
contents: write
statuses: write
id-token: write # aws-actions/configure-aws-credentials
env:
TEST_PG_BENCH_DURATIONS_MATRIX: "1h" # todo update to > 1 h
TEST_PG_BENCH_DURATIONS_MATRIX: "1h" # todo update to > 1 h
TEST_PGBENCH_CUSTOM_SCRIPTS: ${{ matrix.custom_scripts }}
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
PG_VERSION: 16 # pre-determined by pre-determined project
@@ -93,7 +85,7 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Create Neon Branch for large tenant
if: ${{ matrix.target == 'new_branch' }}
@@ -137,7 +129,7 @@ jobs:
${PSQL} "${BENCHMARK_CONNSTR}" -c "SET statement_timeout = 0; DELETE FROM webhook.incoming_webhooks WHERE created_at > '2025-02-27 23:59:59+00';"
echo "$(date '+%Y-%m-%d %H:%M:%S') - Finished deleting rows in table webhook.incoming_webhooks from prior runs"
- name: Benchmark pgbench with custom-scripts
- name: Benchmark pgbench with custom-scripts
uses: ./.github/actions/run-python-test-set
with:
build_type: ${{ env.BUILD_TYPE }}
@@ -146,14 +138,13 @@ jobs:
save_perf_report: true
extra_params: -m remote_cluster --timeout 7200 -k test_perf_oltp_large_tenant_pgbench
pg_version: ${{ env.PG_VERSION }}
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
- name: Benchmark database maintenance
if: ${{ matrix.test_maintenance == 'true' }}
uses: ./.github/actions/run-python-test-set
with:
build_type: ${{ env.BUILD_TYPE }}
@@ -162,7 +153,7 @@ jobs:
save_perf_report: true
extra_params: -m remote_cluster --timeout 172800 -k test_perf_oltp_large_tenant_maintenance
pg_version: ${{ env.PG_VERSION }}
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr_without_pooler }}
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
@@ -188,8 +179,8 @@ jobs:
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
with:
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
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@fcfb566f8b0aab22203f066d80ca1d7e4b5d05b3 # v1.27.1

View File

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

View File

@@ -53,7 +53,7 @@ jobs:
submodules: true
- name: Check for Postgres changes
uses: step-security/paths-filter@v3
uses: dorny/paths-filter@1441771bbfdd59dcd748680ee64ebd8faab1a242 #v3
id: files_changed
with:
token: ${{ github.token }}
@@ -63,14 +63,16 @@ jobs:
- name: Filter out only v-string for build matrix
id: postgres_changes
env:
CHANGES: ${{ steps.files_changed.outputs.changes }}
run: |
v_strings_only_as_json_array=$(echo ${CHANGES} | jq '.[]|select(test("v\\d+"))' | jq --slurp -c)
v_strings_only_as_json_array=$(echo ${{ steps.files_changed.outputs.chnages }} | jq '.[]|select(test("v\\d+"))' | jq --slurp -c)
echo "changes=${v_strings_only_as_json_array}" | tee -a "${GITHUB_OUTPUT}"
check-macos-build:
needs: [ check-permissions, files-changed ]
if: |
contains(github.event.pull_request.labels.*.name, 'run-extra-build-macos') ||
contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
github.ref_name == 'main'
uses: ./.github/workflows/build-macos.yml
with:
pg_versions: ${{ needs.files-changed.outputs.postgres_changes }}

View File

@@ -1,4 +1,4 @@
name: Periodic pagebench performance test on unit-perf hetzner runner
name: Periodic pagebench performance test on dedicated EC2 machine in eu-central-1 region
on:
schedule:
@@ -8,7 +8,7 @@ on:
# │ │ ┌───────────── day of the month (1 - 31)
# │ │ │ ┌───────────── month (1 - 12 or JAN-DEC)
# │ │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
- cron: '0 */4 * * *' # Runs every 4 hours
- cron: '0 */3 * * *' # Runs every 3 hours
workflow_dispatch: # Allows manual triggering of the workflow
inputs:
commit_hash:
@@ -16,11 +16,6 @@ on:
description: 'The long neon repo commit hash for the system under test (pageserver) to be tested.'
required: false
default: ''
recreate_snapshots:
type: boolean
description: 'Recreate snapshots - !!!WARNING!!! We should only recreate snapshots if the previous ones are no longer compatible. Otherwise benchmarking results are not comparable across runs.'
required: false
default: false
defaults:
run:
@@ -34,13 +29,13 @@ permissions:
contents: read
jobs:
run_periodic_pagebench_test:
trigger_bench_on_ec2_machine_in_eu_central_1:
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: write
pull-requests: write
runs-on: [ self-hosted, unit-perf ]
runs-on: [ self-hosted, small ]
container:
image: ghcr.io/neondatabase/build-tools:pinned-bookworm
credentials:
@@ -49,13 +44,10 @@ jobs:
options: --init
timeout-minutes: 360 # Set the timeout to 6 hours
env:
API_KEY: ${{ secrets.PERIODIC_PAGEBENCH_EC2_RUNNER_API_KEY }}
RUN_ID: ${{ github.run_id }}
DEFAULT_PG_VERSION: 16
BUILD_TYPE: release
RUST_BACKTRACE: 1
# NEON_ENV_BUILDER_USE_OVERLAYFS_FOR_SNAPSHOTS: 1 - doesn't work without root in container
S3_BUCKET: neon-github-public-dev
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
AWS_DEFAULT_REGION : "eu-central-1"
AWS_INSTANCE_ID : "i-02a59a3bf86bc7e74"
steps:
# we don't need the neon source code because we run everything remotely
# however we still need the local github actions to run the allure step below
@@ -64,193 +56,98 @@ jobs:
with:
egress-policy: audit
- name: Set up the environment which depends on $RUNNER_TEMP on nvme drive
id: set-env
shell: bash -euxo pipefail {0}
run: |
{
echo "NEON_DIR=${RUNNER_TEMP}/neon"
echo "NEON_BIN=${RUNNER_TEMP}/neon/bin"
echo "POSTGRES_DISTRIB_DIR=${RUNNER_TEMP}/neon/pg_install"
echo "LD_LIBRARY_PATH=${RUNNER_TEMP}/neon/pg_install/v${DEFAULT_PG_VERSION}/lib"
echo "BACKUP_DIR=${RUNNER_TEMP}/instance_store/saved_snapshots"
echo "TEST_OUTPUT=${RUNNER_TEMP}/neon/test_output"
echo "PERF_REPORT_DIR=${RUNNER_TEMP}/neon/test_output/perf-report-local"
echo "ALLURE_DIR=${RUNNER_TEMP}/neon/test_output/allure-results"
echo "ALLURE_RESULTS_DIR=${RUNNER_TEMP}/neon/test_output/allure-results/results"
} >> "$GITHUB_ENV"
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
echo "allure_results_dir=${RUNNER_TEMP}/neon/test_output/allure-results/results" >> "$GITHUB_OUTPUT"
- name: Show my own (github runner) external IP address - usefull for IP allowlisting
run: curl https://ifconfig.me
- uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
- name: Assume AWS OIDC role that allows to manage (start/stop/describe... EC machine)
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 18000 # max 5 hours (needed in case commit hash is still being built)
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_MANAGE_BENCHMARK_EC2_VMS_ARN }}
role-duration-seconds: 3600
- name: Start EC2 instance and wait for the instance to boot up
run: |
aws ec2 start-instances --instance-ids $AWS_INSTANCE_ID
aws ec2 wait instance-running --instance-ids $AWS_INSTANCE_ID
sleep 60 # sleep some time to allow cloudinit and our API server to start up
- name: Determine public IP of the EC2 instance and set env variable EC2_MACHINE_URL_US
run: |
public_ip=$(aws ec2 describe-instances --instance-ids $AWS_INSTANCE_ID --query 'Reservations[*].Instances[*].PublicIpAddress' --output text)
echo "Public IP of the EC2 instance: $public_ip"
echo "EC2_MACHINE_URL_US=https://${public_ip}:8443" >> $GITHUB_ENV
- name: Determine commit hash
id: commit_hash
shell: bash -euxo pipefail {0}
env:
INPUT_COMMIT_HASH: ${{ github.event.inputs.commit_hash }}
run: |
if [[ -z "${INPUT_COMMIT_HASH}" ]]; then
COMMIT_HASH=$(curl -s https://api.github.com/repos/neondatabase/neon/commits/main | jq -r '.sha')
echo "COMMIT_HASH=$COMMIT_HASH" >> $GITHUB_ENV
echo "commit_hash=$COMMIT_HASH" >> "$GITHUB_OUTPUT"
if [ -z "$INPUT_COMMIT_HASH" ]; then
echo "COMMIT_HASH=$(curl -s https://api.github.com/repos/neondatabase/neon/commits/main | jq -r '.sha')" >> $GITHUB_ENV
echo "COMMIT_HASH_TYPE=latest" >> $GITHUB_ENV
else
COMMIT_HASH="${INPUT_COMMIT_HASH}"
echo "COMMIT_HASH=$COMMIT_HASH" >> $GITHUB_ENV
echo "commit_hash=$COMMIT_HASH" >> "$GITHUB_OUTPUT"
echo "COMMIT_HASH=$INPUT_COMMIT_HASH" >> $GITHUB_ENV
echo "COMMIT_HASH_TYPE=manual" >> $GITHUB_ENV
fi
- name: Checkout the neon repository at given commit hash
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
ref: ${{ steps.commit_hash.outputs.commit_hash }}
# does not reuse ./.github/actions/download because we need to download the artifact for the given commit hash
# example artifact
# s3://neon-github-public-dev/artifacts/48b870bc078bd2c450eb7b468e743b9c118549bf/15036827400/1/neon-Linux-X64-release-artifact.tar.zst /instance_store/artifacts/neon-Linux-release-artifact.tar.zst
- name: Determine artifact S3_KEY for given commit hash and download and extract artifact
id: artifact_prefix
shell: bash -euxo pipefail {0}
env:
ARCHIVE: ${{ runner.temp }}/downloads/neon-${{ runner.os }}-${{ runner.arch }}-release-artifact.tar.zst
COMMIT_HASH: ${{ env.COMMIT_HASH }}
COMMIT_HASH_TYPE: ${{ env.COMMIT_HASH_TYPE }}
- name: Start Bench with run_id
run: |
attempt=0
max_attempts=24 # 5 minutes * 24 = 2 hours
curl -k -X 'POST' \
"${EC2_MACHINE_URL_US}/start_test/${GITHUB_RUN_ID}" \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-H "Authorization: Bearer $API_KEY" \
-d "{\"neonRepoCommitHash\": \"${COMMIT_HASH}\", \"neonRepoCommitHashType\": \"${COMMIT_HASH_TYPE}\"}"
while [[ $attempt -lt $max_attempts ]]; do
# the following command will fail until the artifacts are available ...
S3_KEY=$(aws s3api list-objects-v2 --bucket "$S3_BUCKET" --prefix "artifacts/$COMMIT_HASH/" \
| jq -r '.Contents[]?.Key' \
| grep "neon-${{ runner.os }}-${{ runner.arch }}-release-artifact.tar.zst" \
| sort --version-sort \
| tail -1) || true # ... thus ignore errors from the command
if [[ -n "${S3_KEY}" ]]; then
echo "Artifact found: $S3_KEY"
echo "S3_KEY=$S3_KEY" >> $GITHUB_ENV
- name: Poll Test Status
id: poll_step
run: |
status=""
while [[ "$status" != "failure" && "$status" != "success" ]]; do
response=$(curl -k -X 'GET' \
"${EC2_MACHINE_URL_US}/test_status/${GITHUB_RUN_ID}" \
-H 'accept: application/json' \
-H "Authorization: Bearer $API_KEY")
echo "Response: $response"
set +x
status=$(echo $response | jq -r '.status')
echo "Test status: $status"
if [[ "$status" == "failure" ]]; then
echo "Test failed"
exit 1 # Fail the job step if status is failure
elif [[ "$status" == "success" || "$status" == "null" ]]; then
break
elif [[ "$status" == "too_many_runs" ]]; then
echo "Too many runs already running"
echo "too_many_runs=true" >> "$GITHUB_OUTPUT"
exit 1
fi
# Increment attempt counter and sleep for 5 minutes
attempt=$((attempt + 1))
echo "Attempt $attempt of $max_attempts to find artifacts in S3 bucket s3://$S3_BUCKET/artifacts/$COMMIT_HASH failed. Retrying in 5 minutes..."
sleep 300 # Sleep for 5 minutes
sleep 60 # Poll every 60 seconds
done
if [[ -z "${S3_KEY}" ]]; then
echo "Error: artifact not found in S3 bucket s3://$S3_BUCKET/artifacts/$COMMIT_HASH" after 2 hours
else
mkdir -p $(dirname $ARCHIVE)
time aws s3 cp --only-show-errors s3://$S3_BUCKET/${S3_KEY} ${ARCHIVE}
mkdir -p ${NEON_DIR}
time tar -xf ${ARCHIVE} -C ${NEON_DIR}
rm -f ${ARCHIVE}
fi
- name: Download snapshots from S3
if: ${{ github.event_name != 'workflow_dispatch' || github.event.inputs.recreate_snapshots == 'false' || github.event.inputs.recreate_snapshots == '' }}
id: download_snapshots
shell: bash -euxo pipefail {0}
- name: Retrieve Test Logs
if: always() && steps.poll_step.outputs.too_many_runs != 'true'
run: |
# Download the snapshots from S3
mkdir -p ${TEST_OUTPUT}
mkdir -p $BACKUP_DIR
cd $BACKUP_DIR
mkdir parts
cd parts
PART=$(aws s3api list-objects-v2 --bucket $S3_BUCKET --prefix performance/pagebench/ \
| jq -r '.Contents[]?.Key' \
| grep -E 'shared-snapshots-[0-9]{4}-[0-9]{2}-[0-9]{2}' \
| sort \
| tail -1)
echo "Latest PART: $PART"
if [[ -z "$PART" ]]; then
echo "ERROR: No matching S3 key found" >&2
exit 1
fi
S3_KEY=$(dirname $PART)
time aws s3 cp --only-show-errors --recursive s3://${S3_BUCKET}/$S3_KEY/ .
cd $TEST_OUTPUT
time cat $BACKUP_DIR/parts/* | zstdcat | tar --extract --preserve-permissions
rm -rf ${BACKUP_DIR}
curl -k -X 'GET' \
"${EC2_MACHINE_URL_US}/test_log/${GITHUB_RUN_ID}" \
-H 'accept: application/gzip' \
-H "Authorization: Bearer $API_KEY" \
--output "test_log_${GITHUB_RUN_ID}.gz"
- name: Cache poetry deps
uses: actions/cache@v4
with:
path: ~/.cache/pypoetry/virtualenvs
key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-bookworm-${{ hashFiles('poetry.lock') }}
- name: Install Python deps
shell: bash -euxo pipefail {0}
run: ./scripts/pysync
# we need high number of open files for pagebench
- name: show ulimits
shell: bash -euxo pipefail {0}
- name: Unzip Test Log and Print it into this job's log
if: always() && steps.poll_step.outputs.too_many_runs != 'true'
run: |
ulimit -a
- name: Run pagebench testcase
shell: bash -euxo pipefail {0}
env:
CI: false # need to override this env variable set by github to enforce using snapshots
run: |
export PLATFORM=hetzner-unit-perf-${COMMIT_HASH_TYPE}
# report the commit hash of the neon repository in the revision of the test results
export GITHUB_SHA=${COMMIT_HASH}
rm -rf ${PERF_REPORT_DIR}
rm -rf ${ALLURE_RESULTS_DIR}
mkdir -p ${PERF_REPORT_DIR}
mkdir -p ${ALLURE_RESULTS_DIR}
PARAMS="--alluredir=${ALLURE_RESULTS_DIR} --tb=short --verbose -rA"
EXTRA_PARAMS="--out-dir ${PERF_REPORT_DIR} --durations-path $TEST_OUTPUT/benchmark_durations.json"
# run only two selected tests
# environment set by parent:
# RUST_BACKTRACE=1 DEFAULT_PG_VERSION=16 BUILD_TYPE=release
./scripts/pytest ${PARAMS} test_runner/performance/pageserver/pagebench/test_pageserver_max_throughput_getpage_at_latest_lsn.py::test_pageserver_characterize_throughput_with_n_tenants ${EXTRA_PARAMS}
./scripts/pytest ${PARAMS} test_runner/performance/pageserver/pagebench/test_pageserver_max_throughput_getpage_at_latest_lsn.py::test_pageserver_characterize_latencies_with_1_client_and_throughput_with_many_clients_one_tenant ${EXTRA_PARAMS}
- name: upload the performance metrics to the Neon performance database which is used by grafana dashboards to display the results
shell: bash -euxo pipefail {0}
run: |
export REPORT_FROM="$PERF_REPORT_DIR"
export GITHUB_SHA=${COMMIT_HASH}
time ./scripts/generate_and_push_perf_report.sh
- name: Upload test results
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-store
with:
report-dir: ${{ steps.set-env.outputs.allure_results_dir }}
unique-key: ${{ env.BUILD_TYPE }}-${{ env.DEFAULT_PG_VERSION }}-${{ runner.arch }}
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
gzip -d "test_log_${GITHUB_RUN_ID}.gz"
cat "test_log_${GITHUB_RUN_ID}"
- name: Create Allure report
id: create-allure-report
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
with:
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Upload snapshots
if: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.recreate_snapshots != 'false' && github.event.inputs.recreate_snapshots != '' }}
id: upload_snapshots
shell: bash -euxo pipefail {0}
run: |
mkdir -p $BACKUP_DIR
cd $TEST_OUTPUT
tar --create --preserve-permissions --file - shared-snapshots | zstd -o $BACKUP_DIR/shared_snapshots.tar.zst
cd $BACKUP_DIR
mkdir parts
split -b 1G shared_snapshots.tar.zst ./parts/shared_snapshots.tar.zst.part.
SNAPSHOT_DATE=$(date +%F) # YYYY-MM-DD
cd parts
time aws s3 cp --recursive . s3://${S3_BUCKET}/performance/pagebench/shared-snapshots-${SNAPSHOT_DATE}/
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
@@ -260,22 +157,26 @@ jobs:
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()
shell: bash -euxo pipefail {0}
env:
ARCHIVE: ${{ runner.temp }}/downloads/neon-${{ runner.os }}-${{ runner.arch }}-release-artifact.tar.zst
run: |
# Cleanup the test resources
if [[ -d "${BACKUP_DIR}" ]]; then
rm -rf ${BACKUP_DIR}
fi
if [[ -d "${TEST_OUTPUT}" ]]; then
rm -rf ${TEST_OUTPUT}
fi
if [[ -d "${NEON_DIR}" ]]; then
rm -rf ${NEON_DIR}
fi
rm -rf $(dirname $ARCHIVE)
curl -k -X 'POST' \
"${EC2_MACHINE_URL_US}/cleanup_test/${GITHUB_RUN_ID}" \
-H 'accept: application/json' \
-H "Authorization: Bearer $API_KEY" \
-d ''
- name: Assume AWS OIDC role that allows to manage (start/stop/describe... EC machine)
if: always() && steps.poll_step.outputs.too_many_runs != 'true'
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_MANAGE_BENCHMARK_EC2_VMS_ARN }}
role-duration-seconds: 3600
- name: Stop EC2 instance and wait for the instance to be stopped
if: always() && steps.poll_step.outputs.too_many_runs != 'true'
run: |
aws ec2 stop-instances --instance-ids $AWS_INSTANCE_ID
aws ec2 wait instance-stopped --instance-ids $AWS_INSTANCE_ID

View File

@@ -103,7 +103,7 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Create Neon Project
id: create-neon-project
@@ -122,7 +122,7 @@ jobs:
run_in_parallel: false
extra_params: -m remote_cluster
pg_version: ${{ env.DEFAULT_PG_VERSION }}
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
BENCHMARK_CONNSTR: ${{ steps.create-neon-project.outputs.dsn }}
@@ -139,7 +139,7 @@ jobs:
uses: ./.github/actions/allure-report-generate
with:
store-test-results-into-db: true
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
@@ -178,7 +178,7 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Create Neon Project
id: create-neon-project
@@ -195,7 +195,7 @@ jobs:
run_in_parallel: false
extra_params: -m remote_cluster
pg_version: ${{ env.DEFAULT_PG_VERSION }}
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
BENCHMARK_CONNSTR: ${{ steps.create-neon-project.outputs.dsn }}
@@ -212,7 +212,7 @@ jobs:
uses: ./.github/actions/allure-report-generate
with:
store-test-results-into-db: true
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}

View File

@@ -41,7 +41,7 @@ jobs:
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@0634a2670c59f64b4a01f0f96f84700a4088b9f0 # v2.12.0
uses: step-security/harden-runner@v2
with:
egress-policy: audit

View File

@@ -1,83 +0,0 @@
name: Periodic proxy performance test on unit-perf hetzner runner
on:
push: # TODO: remove after testing
branches:
- test-proxy-bench # Runs on pushes to branches starting with test-proxy-bench
# schedule:
# * is a special character in YAML so you have to quote this string
# ┌───────────── minute (0 - 59)
# │ ┌───────────── hour (0 - 23)
# │ │ ┌───────────── day of the month (1 - 31)
# │ │ │ ┌───────────── month (1 - 12 or JAN-DEC)
# │ │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
# - cron: '0 5 * * *' # Runs at 5 UTC once a day
workflow_dispatch: # adds an ability to run this manually
defaults:
run:
shell: bash -euo pipefail {0}
concurrency:
group: ${{ github.workflow }}
cancel-in-progress: false
permissions:
contents: read
jobs:
run_periodic_proxybench_test:
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: write
pull-requests: write
runs-on: [self-hosted, unit-perf]
timeout-minutes: 60 # 1h timeout
container:
image: ghcr.io/neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
steps:
- name: Checkout proxy-bench Repo
uses: actions/checkout@v4
with:
repository: neondatabase/proxy-bench
path: proxy-bench
- name: Set up the environment which depends on $RUNNER_TEMP on nvme drive
id: set-env
shell: bash -euxo pipefail {0}
run: |
PROXY_BENCH_PATH=$(realpath ./proxy-bench)
{
echo "PROXY_BENCH_PATH=$PROXY_BENCH_PATH"
echo "NEON_DIR=${RUNNER_TEMP}/neon"
echo "TEST_OUTPUT=${PROXY_BENCH_PATH}/test_output"
echo ""
} >> "$GITHUB_ENV"
- name: Run proxy-bench
run: ./${PROXY_BENCH_PATH}/run.sh
- name: Ingest Bench Results # neon repo script
if: success()
run: |
mkdir -p $TEST_OUTPUT
python $NEON_DIR/scripts/proxy_bench_results_ingest.py --out $TEST_OUTPUT
- name: Push Metrics to Proxy perf database
if: success()
env:
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PROXY_TEST_RESULT_CONNSTR }}"
REPORT_FROM: $TEST_OUTPUT
run: $NEON_DIR/scripts/generate_and_push_perf_report.sh
- name: Docker cleanup
run: docker compose down
- name: Notify Failure
if: failure()
run: echo "Proxy bench job failed" && exit 1

View File

@@ -66,7 +66,7 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Run tests
uses: ./.github/actions/run-python-test-set
@@ -76,7 +76,7 @@ jobs:
run_in_parallel: false
extra_params: -m remote_cluster
pg_version: ${{ matrix.pg-version }}
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
NEON_API_KEY: ${{ secrets.NEON_STAGING_API_KEY }}
RANDOM_SEED: ${{ inputs.random_seed }}
@@ -88,6 +88,6 @@ jobs:
uses: ./.github/actions/allure-report-generate
with:
store-test-results-into-db: true
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}

View File

@@ -1,12 +0,0 @@
name: Create compute release PR
on:
schedule:
- cron: '0 7 * * FRI'
jobs:
create-release-pr:
uses: ./.github/workflows/release.yml
with:
component: compute
secrets: inherit

View File

@@ -1,12 +0,0 @@
name: Create proxy release PR
on:
schedule:
- cron: '0 6 * * TUE'
jobs:
create-release-pr:
uses: ./.github/workflows/release.yml
with:
component: proxy
secrets: inherit

View File

@@ -1,12 +0,0 @@
name: Create storage release PR
on:
schedule:
- cron: '0 6 * * FRI'
jobs:
create-release-pr:
uses: ./.github/workflows/release.yml
with:
component: storage
secrets: inherit

View File

@@ -1,34 +1,25 @@
name: Create release PR
name: Create Release Branch
on:
schedule:
# It should be kept in sync with if-condition in jobs
- cron: '0 6 * * TUE' # Proxy release
- cron: '0 6 * * FRI' # Storage release
- cron: '0 7 * * FRI' # Compute release
workflow_dispatch:
inputs:
component:
description: "Component to release"
required: true
type: choice
options:
- compute
- proxy
- storage
cherry-pick:
description: "Commits to cherry-pick (space separated, makes this a hotfix based on previous release)"
create-storage-release-branch:
type: boolean
description: 'Create Storage release PR'
required: false
type: string
default: ''
workflow_call:
inputs:
component:
description: "Component to release"
required: true
type: string
cherry-pick:
description: "Commits to cherry-pick (space separated, makes this a hotfix based on previous release)"
create-proxy-release-branch:
type: boolean
description: 'Create Proxy release PR'
required: false
create-compute-release-branch:
type: boolean
description: 'Create Compute release PR'
required: false
type: string
default: ''
# No permission for GITHUB_TOKEN by default; the **minimal required** set of permissions should be granted in each job.
permissions: {}
@@ -38,31 +29,41 @@ defaults:
shell: bash -euo pipefail {0}
jobs:
create-release-pr:
runs-on: ubuntu-22.04
create-storage-release-branch:
if: ${{ github.event.schedule == '0 6 * * FRI' || inputs.create-storage-release-branch }}
permissions:
contents: write
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
uses: ./.github/workflows/_create-release-pr.yml
with:
component-name: 'Storage'
source-branch: ${{ github.ref_name }}
secrets:
ci-access-token: ${{ secrets.CI_ACCESS_TOKEN }}
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
fetch-depth: 0
create-proxy-release-branch:
if: ${{ github.event.schedule == '0 6 * * TUE' || inputs.create-proxy-release-branch }}
- name: Configure git
run: |
git config user.name "github-actions[bot]"
git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
permissions:
contents: write
- name: Create release PR
uses: neondatabase/dev-actions/release-pr@290dec821d86fa8a93f019e8c69720f5865b5677
with:
component: ${{ inputs.component }}
cherry-pick: ${{ inputs.cherry-pick }}
env:
GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
uses: ./.github/workflows/_create-release-pr.yml
with:
component-name: 'Proxy'
source-branch: ${{ github.ref_name }}
secrets:
ci-access-token: ${{ secrets.CI_ACCESS_TOKEN }}
create-compute-release-branch:
if: ${{ github.event.schedule == '0 7 * * FRI' || inputs.create-compute-release-branch }}
permissions:
contents: write
uses: ./.github/workflows/_create-release-pr.yml
with:
component-name: 'Compute'
source-branch: ${{ github.ref_name }}
secrets:
ci-access-token: ${{ secrets.CI_ACCESS_TOKEN }}

View File

@@ -35,7 +35,7 @@ jobs:
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@0634a2670c59f64b4a01f0f96f84700a4088b9f0 # v2.12.0
uses: step-security/harden-runner@v2
with:
egress-policy: audit
@@ -73,7 +73,7 @@ jobs:
}}
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@0634a2670c59f64b4a01f0f96f84700a4088b9f0 # v2.12.0
uses: step-security/harden-runner@v2
with:
egress-policy: audit

1
.gitignore vendored
View File

@@ -1,5 +1,4 @@
/artifact_cache
/build
/pg_install
/target
/tmp_check

412
Cargo.lock generated

File diff suppressed because it is too large Load Diff

View File

@@ -9,7 +9,6 @@ members = [
"pageserver/ctl",
"pageserver/client",
"pageserver/pagebench",
"pageserver/page_api",
"proxy",
"safekeeper",
"safekeeper/client",
@@ -22,15 +21,11 @@ members = [
"libs/http-utils",
"libs/pageserver_api",
"libs/postgres_ffi",
"libs/postgres_ffi_types",
"libs/postgres_versioninfo",
"libs/safekeeper_api",
"libs/desim",
"libs/neon-shmem",
"libs/utils",
"libs/consumption_metrics",
"libs/postgres_backend",
"libs/posthog_client_lite",
"libs/pq_proto",
"libs/tenant_size_model",
"libs/metrics",
@@ -73,8 +68,8 @@ aws-credential-types = "1.2.0"
aws-sigv4 = { version = "1.2", features = ["sign-http"] }
aws-types = "1.3"
axum = { version = "0.8.1", features = ["ws"] }
axum-extra = { version = "0.10.0", features = ["typed-header", "query"] }
base64 = "0.22"
axum-extra = { version = "0.10.0", features = ["typed-header"] }
base64 = "0.13.0"
bincode = "1.3"
bindgen = "0.71"
bit_field = "0.10.2"
@@ -131,7 +126,7 @@ md5 = "0.7.0"
measured = { version = "0.0.22", features=["lasso"] }
measured-process = { version = "0.0.22" }
memoffset = "0.9"
nix = { version = "0.30.1", features = ["dir", "fs", "mman", "process", "socket", "signal", "poll"] }
nix = { version = "0.27", features = ["dir", "fs", "process", "socket", "signal", "poll"] }
# Do not update to >= 7.0.0, at least. The update will have a significant impact
# on compute startup metrics (start_postgres_ms), >= 25% degradation.
notify = "6.0.0"
@@ -151,7 +146,7 @@ pin-project-lite = "0.2"
pprof = { version = "0.14", features = ["criterion", "flamegraph", "frame-pointer", "prost-codec"] }
procfs = "0.16"
prometheus = {version = "0.13", default-features=false, features = ["process"]} # removes protobuf dependency
prost = "0.13.5"
prost = "0.13"
rand = "0.8"
redis = { version = "0.29.2", features = ["tokio-rustls-comp", "keep-alive"] }
regex = "1.10.2"
@@ -173,9 +168,8 @@ sentry = { version = "0.37", default-features = false, features = ["backtrace",
serde = { version = "1.0", features = ["derive"] }
serde_json = "1"
serde_path_to_error = "0.1"
serde_with = { version = "3", features = [ "base64" ] }
serde_with = { version = "2.0", features = [ "base64" ] }
serde_assert = "0.5.0"
serde_repr = "0.1.20"
sha2 = "0.10.2"
signal-hook = "0.3"
smallvec = "1.11"
@@ -202,8 +196,7 @@ tokio-tar = "0.3"
tokio-util = { version = "0.7.10", features = ["io", "rt"] }
toml = "0.8"
toml_edit = "0.22"
tonic = { version = "0.13.1", default-features = false, features = ["channel", "codegen", "gzip", "prost", "router", "server", "tls-ring", "tls-native-roots", "zstd"] }
tonic-reflection = { version = "0.13.1", features = ["server"] }
tonic = {version = "0.12.3", default-features = false, features = ["channel", "tls", "tls-roots"]}
tower = { version = "0.5.2", default-features = false }
tower-http = { version = "0.6.2", features = ["auth", "request-id", "trace"] }
@@ -250,34 +243,29 @@ azure_storage_blobs = { git = "https://github.com/neondatabase/azure-sdk-for-rus
## Local libraries
compute_api = { version = "0.1", path = "./libs/compute_api/" }
consumption_metrics = { version = "0.1", path = "./libs/consumption_metrics/" }
desim = { version = "0.1", path = "./libs/desim" }
endpoint_storage = { version = "0.0.1", path = "./endpoint_storage/" }
http-utils = { version = "0.1", path = "./libs/http-utils/" }
metrics = { version = "0.1", path = "./libs/metrics/" }
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/" }
pageserver_page_api = { path = "./pageserver/page_api" }
postgres_backend = { version = "0.1", path = "./libs/postgres_backend/" }
postgres_connection = { version = "0.1", path = "./libs/postgres_connection/" }
postgres_ffi = { version = "0.1", path = "./libs/postgres_ffi/" }
postgres_ffi_types = { version = "0.1", path = "./libs/postgres_ffi_types/" }
postgres_versioninfo = { version = "0.1", path = "./libs/postgres_versioninfo/" }
postgres_initdb = { path = "./libs/postgres_initdb" }
posthog_client_lite = { version = "0.1", path = "./libs/posthog_client_lite" }
pq_proto = { version = "0.1", path = "./libs/pq_proto/" }
remote_storage = { version = "0.1", path = "./libs/remote_storage/" }
safekeeper_api = { version = "0.1", path = "./libs/safekeeper_api" }
safekeeper_client = { path = "./safekeeper/client" }
desim = { version = "0.1", path = "./libs/desim" }
storage_broker = { version = "0.1", path = "./storage_broker/" } # Note: main broker code is inside the binary crate, so linking with the library shouldn't be heavy.
storage_controller_client = { path = "./storage_controller/client" }
tenant_size_model = { version = "0.1", path = "./libs/tenant_size_model/" }
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/" }
wal_decoder = { version = "0.1", path = "./libs/wal_decoder" }
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/" }
@@ -287,7 +275,7 @@ criterion = "0.5.1"
rcgen = "0.13"
rstest = "0.18"
camino-tempfile = "1.0.2"
tonic-build = "0.13.1"
tonic-build = "0.12"
[patch.crates-io]

View File

@@ -5,6 +5,8 @@
ARG REPOSITORY=ghcr.io/neondatabase
ARG IMAGE=build-tools
ARG TAG=pinned
ARG DEFAULT_PG_VERSION=17
ARG STABLE_PG_VERSION=16
ARG DEBIAN_VERSION=bookworm
ARG DEBIAN_FLAVOR=${DEBIAN_VERSION}-slim
@@ -45,6 +47,7 @@ COPY --chown=nonroot scripts/ninstall.sh scripts/ninstall.sh
ENV BUILD_TYPE=release
RUN set -e \
&& mold -run make -j $(nproc) -s neon-pg-ext \
&& rm -rf pg_install/build \
&& tar -C pg_install -czf /home/nonroot/postgres_install.tar.gz .
# Prepare cargo-chef recipe
@@ -60,11 +63,14 @@ FROM $REPOSITORY/$IMAGE:$TAG AS build
WORKDIR /home/nonroot
ARG GIT_VERSION=local
ARG BUILD_TAG
ARG STABLE_PG_VERSION
COPY --from=pg-build /home/nonroot/pg_install/v14/include/postgresql/server pg_install/v14/include/postgresql/server
COPY --from=pg-build /home/nonroot/pg_install/v15/include/postgresql/server pg_install/v15/include/postgresql/server
COPY --from=pg-build /home/nonroot/pg_install/v16/include/postgresql/server pg_install/v16/include/postgresql/server
COPY --from=pg-build /home/nonroot/pg_install/v17/include/postgresql/server pg_install/v17/include/postgresql/server
COPY --from=pg-build /home/nonroot/pg_install/v16/lib pg_install/v16/lib
COPY --from=pg-build /home/nonroot/pg_install/v17/lib pg_install/v17/lib
COPY --from=plan /home/nonroot/recipe.json recipe.json
ARG ADDITIONAL_RUSTFLAGS=""
@@ -91,6 +97,7 @@ RUN set -e \
# Build final image
#
FROM $BASE_IMAGE_SHA
ARG DEFAULT_PG_VERSION
WORKDIR /data
RUN set -e \
@@ -100,20 +107,9 @@ RUN set -e \
libreadline-dev \
libseccomp-dev \
ca-certificates \
# System postgres for use with client libraries (e.g. in storage controller)
postgresql-15 \
openssl \
unzip \
curl \
&& ARCH=$(uname -m) \
&& if [ "$ARCH" = "x86_64" ]; then \
curl "https://awscli.amazonaws.com/awscli-exe-linux-x86_64.zip" -o "awscliv2.zip"; \
elif [ "$ARCH" = "aarch64" ]; then \
curl "https://awscli.amazonaws.com/awscli-exe-linux-aarch64.zip" -o "awscliv2.zip"; \
else \
echo "Unsupported architecture: $ARCH" && exit 1; \
fi \
&& unzip awscliv2.zip \
&& ./aws/install \
&& rm -rf aws awscliv2.zip \
&& rm -f /etc/apt/apt.conf.d/80-retries \
&& rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* \
&& useradd -d /data neon \

163
Makefile
View File

@@ -1,18 +1,8 @@
ROOT_PROJECT_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
# Where to install Postgres, default is ./pg_install, maybe useful for package
# managers.
# Where to install Postgres, default is ./pg_install, maybe useful for package managers
POSTGRES_INSTALL_DIR ?= $(ROOT_PROJECT_DIR)/pg_install/
# CARGO_BUILD_FLAGS: Extra flags to pass to `cargo build`. `--locked`
# and `--features testing` are popular examples.
#
# CARGO_PROFILE: You can also set to override the cargo profile to
# use. By default, it is derived from BUILD_TYPE.
# All intermediate build artifacts are stored here.
BUILD_DIR := build
ICU_PREFIX_DIR := /usr/local/icu
#
@@ -26,12 +16,12 @@ ifeq ($(BUILD_TYPE),release)
PG_CONFIGURE_OPTS = --enable-debug --with-openssl
PG_CFLAGS += -O2 -g3 $(CFLAGS)
PG_LDFLAGS = $(LDFLAGS)
CARGO_PROFILE ?= --profile=release
# Unfortunately, `--profile=...` is a nightly feature
CARGO_BUILD_FLAGS += --release
else ifeq ($(BUILD_TYPE),debug)
PG_CONFIGURE_OPTS = --enable-debug --with-openssl --enable-cassert --enable-depend
PG_CFLAGS += -O0 -g3 $(CFLAGS)
PG_LDFLAGS = $(LDFLAGS)
CARGO_PROFILE ?= --profile=dev
else
$(error Bad build type '$(BUILD_TYPE)', see Makefile for options)
endif
@@ -103,7 +93,7 @@ all: neon postgres neon-pg-ext
.PHONY: neon
neon: postgres-headers walproposer-lib cargo-target-dir
+@echo "Compiling Neon"
$(CARGO_CMD_PREFIX) cargo build $(CARGO_BUILD_FLAGS) $(CARGO_PROFILE)
$(CARGO_CMD_PREFIX) cargo build $(CARGO_BUILD_FLAGS)
.PHONY: cargo-target-dir
cargo-target-dir:
# https://github.com/rust-lang/cargo/issues/14281
@@ -114,20 +104,21 @@ cargo-target-dir:
# Some rules are duplicated for Postgres v14 and 15. We may want to refactor
# to avoid the duplication in the future, but it's tolerable for now.
#
$(BUILD_DIR)/%/config.status:
mkdir -p $(BUILD_DIR)
test -e $(BUILD_DIR)/CACHEDIR.TAG || echo "$(CACHEDIR_TAG_CONTENTS)" > $(BUILD_DIR)/CACHEDIR.TAG
$(POSTGRES_INSTALL_DIR)/build/%/config.status:
mkdir -p $(POSTGRES_INSTALL_DIR)
test -e $(POSTGRES_INSTALL_DIR)/CACHEDIR.TAG || echo "$(CACHEDIR_TAG_CONTENTS)" > $(POSTGRES_INSTALL_DIR)/CACHEDIR.TAG
+@echo "Configuring Postgres $* build"
@test -s $(ROOT_PROJECT_DIR)/vendor/postgres-$*/configure || { \
echo "\nPostgres submodule not found in $(ROOT_PROJECT_DIR)/vendor/postgres-$*/, execute "; \
echo "'git submodule update --init --recursive --depth 2 --progress .' in project root.\n"; \
exit 1; }
mkdir -p $(BUILD_DIR)/$*
mkdir -p $(POSTGRES_INSTALL_DIR)/build/$*
VERSION=$*; \
EXTRA_VERSION=$$(cd $(ROOT_PROJECT_DIR)/vendor/postgres-$$VERSION && git rev-parse HEAD); \
(cd $(BUILD_DIR)/$$VERSION && \
(cd $(POSTGRES_INSTALL_DIR)/build/$$VERSION && \
env PATH="$(EXTRA_PATH_OVERRIDES):$$PATH" $(ROOT_PROJECT_DIR)/vendor/postgres-$$VERSION/configure \
CFLAGS='$(PG_CFLAGS)' LDFLAGS='$(PG_LDFLAGS)' \
$(PG_CONFIGURE_OPTS) --with-extra-version=" ($$EXTRA_VERSION)" \
@@ -139,56 +130,96 @@ $(BUILD_DIR)/%/config.status:
# the "build-all-versions" entry points) where direct mention of PostgreSQL
# versions is used.
.PHONY: postgres-configure-v17
postgres-configure-v17: $(BUILD_DIR)/v17/config.status
postgres-configure-v17: $(POSTGRES_INSTALL_DIR)/build/v17/config.status
.PHONY: postgres-configure-v16
postgres-configure-v16: $(BUILD_DIR)/v16/config.status
postgres-configure-v16: $(POSTGRES_INSTALL_DIR)/build/v16/config.status
.PHONY: postgres-configure-v15
postgres-configure-v15: $(BUILD_DIR)/v15/config.status
postgres-configure-v15: $(POSTGRES_INSTALL_DIR)/build/v15/config.status
.PHONY: postgres-configure-v14
postgres-configure-v14: $(BUILD_DIR)/v14/config.status
postgres-configure-v14: $(POSTGRES_INSTALL_DIR)/build/v14/config.status
# Install just the PostgreSQL header files into $(POSTGRES_INSTALL_DIR)/<version>/include
#
# This is implicitly included in the 'postgres-%' rule, but this can be handy if you
# want to just install the headers without building PostgreSQL, e.g. for building
# extensions.
# Install the PostgreSQL header files into $(POSTGRES_INSTALL_DIR)/<version>/include
.PHONY: postgres-headers-%
postgres-headers-%: postgres-configure-%
+@echo "Installing PostgreSQL $* headers"
$(MAKE) -C $(BUILD_DIR)/$*/src/include MAKELEVEL=0 install
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/src/include MAKELEVEL=0 install
# Compile and install PostgreSQL
.PHONY: postgres-%
postgres-%: postgres-configure-% \
postgres-headers-% # to prevent `make install` conflicts with neon's `postgres-headers`
+@echo "Compiling PostgreSQL $*"
$(MAKE) -C $(BUILD_DIR)/$* MAKELEVEL=0 install
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$* MAKELEVEL=0 install
+@echo "Compiling libpq $*"
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/src/interfaces/libpq install
+@echo "Compiling pg_prewarm $*"
$(MAKE) -C $(BUILD_DIR)/$*/contrib/pg_prewarm install
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pg_prewarm install
+@echo "Compiling pg_buffercache $*"
$(MAKE) -C $(BUILD_DIR)/$*/contrib/pg_buffercache install
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pg_buffercache install
+@echo "Compiling pg_visibility $*"
$(MAKE) -C $(BUILD_DIR)/$*/contrib/pg_visibility install
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pg_visibility install
+@echo "Compiling pageinspect $*"
$(MAKE) -C $(BUILD_DIR)/$*/contrib/pageinspect install
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pageinspect install
+@echo "Compiling pg_trgm $*"
$(MAKE) -C $(BUILD_DIR)/$*/contrib/pg_trgm install
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pg_trgm install
+@echo "Compiling amcheck $*"
$(MAKE) -C $(BUILD_DIR)/$*/contrib/amcheck install
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/amcheck install
+@echo "Compiling test_decoding $*"
$(MAKE) -C $(BUILD_DIR)/$*/contrib/test_decoding install
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/test_decoding install
.PHONY: postgres-clean-%
postgres-clean-%:
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$* MAKELEVEL=0 clean
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pg_buffercache clean
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pageinspect clean
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/src/interfaces/libpq clean
.PHONY: postgres-check-%
postgres-check-%: postgres-%
$(MAKE) -C $(BUILD_DIR)/$* MAKELEVEL=0 check
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$* MAKELEVEL=0 check
.PHONY: neon-pg-ext-%
neon-pg-ext-%: postgres-%
+@echo "Compiling neon-specific Postgres extensions for $*"
mkdir -p $(BUILD_DIR)/pgxn-$*
+@echo "Compiling neon $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
-C $(BUILD_DIR)/pgxn-$*\
-f $(ROOT_PROJECT_DIR)/pgxn/Makefile install
-C $(POSTGRES_INSTALL_DIR)/build/neon-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile install
+@echo "Compiling neon_walredo $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-walredo-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-walredo-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_walredo/Makefile install
+@echo "Compiling neon_rmgr $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-rmgr-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-rmgr-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_rmgr/Makefile install
+@echo "Compiling neon_test_utils $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_test_utils/Makefile install
+@echo "Compiling neon_utils $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-utils-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config COPT='$(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-utils-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_utils/Makefile install
.PHONY: neon-pg-clean-ext-%
neon-pg-clean-ext-%:
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config \
-C $(POSTGRES_INSTALL_DIR)/build/neon-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile clean
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config \
-C $(POSTGRES_INSTALL_DIR)/build/neon-walredo-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_walredo/Makefile clean
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config \
-C $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_test_utils/Makefile clean
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config \
-C $(POSTGRES_INSTALL_DIR)/build/neon-utils-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_utils/Makefile clean
# Build walproposer as a static library. walproposer source code is located
# in the pgxn/neon directory.
@@ -202,15 +233,15 @@ neon-pg-ext-%: postgres-%
.PHONY: walproposer-lib
walproposer-lib: neon-pg-ext-v17
+@echo "Compiling walproposer-lib"
mkdir -p $(BUILD_DIR)/walproposer-lib
mkdir -p $(POSTGRES_INSTALL_DIR)/build/walproposer-lib
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v17/bin/pg_config COPT='$(COPT)' \
-C $(BUILD_DIR)/walproposer-lib \
-C $(POSTGRES_INSTALL_DIR)/build/walproposer-lib \
-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile walproposer-lib
cp $(POSTGRES_INSTALL_DIR)/v17/lib/libpgport.a $(BUILD_DIR)/walproposer-lib
cp $(POSTGRES_INSTALL_DIR)/v17/lib/libpgcommon.a $(BUILD_DIR)/walproposer-lib
$(AR) d $(BUILD_DIR)/walproposer-lib/libpgport.a \
cp $(POSTGRES_INSTALL_DIR)/v17/lib/libpgport.a $(POSTGRES_INSTALL_DIR)/build/walproposer-lib
cp $(POSTGRES_INSTALL_DIR)/v17/lib/libpgcommon.a $(POSTGRES_INSTALL_DIR)/build/walproposer-lib
$(AR) d $(POSTGRES_INSTALL_DIR)/build/walproposer-lib/libpgport.a \
pg_strong_random.o
$(AR) d $(BUILD_DIR)/walproposer-lib/libpgcommon.a \
$(AR) d $(POSTGRES_INSTALL_DIR)/build/walproposer-lib/libpgcommon.a \
checksum_helper.o \
cryptohash_openssl.o \
hmac_openssl.o \
@@ -218,10 +249,16 @@ walproposer-lib: neon-pg-ext-v17
parse_manifest.o \
scram-common.o
ifeq ($(UNAME_S),Linux)
$(AR) d $(BUILD_DIR)/walproposer-lib/libpgcommon.a \
$(AR) d $(POSTGRES_INSTALL_DIR)/build/walproposer-lib/libpgcommon.a \
pg_crc32c.o
endif
.PHONY: walproposer-lib-clean
walproposer-lib-clean:
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v17/bin/pg_config \
-C $(POSTGRES_INSTALL_DIR)/build/walproposer-lib \
-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile clean
.PHONY: neon-pg-ext
neon-pg-ext: \
neon-pg-ext-v14 \
@@ -229,6 +266,13 @@ neon-pg-ext: \
neon-pg-ext-v16 \
neon-pg-ext-v17
.PHONY: neon-pg-clean-ext
neon-pg-clean-ext: \
neon-pg-clean-ext-v14 \
neon-pg-clean-ext-v15 \
neon-pg-clean-ext-v16 \
neon-pg-clean-ext-v17
# shorthand to build all Postgres versions
.PHONY: postgres
postgres: \
@@ -244,6 +288,13 @@ postgres-headers: \
postgres-headers-v16 \
postgres-headers-v17
.PHONY: postgres-clean
postgres-clean: \
postgres-clean-v14 \
postgres-clean-v15 \
postgres-clean-v16 \
postgres-clean-v17
.PHONY: postgres-check
postgres-check: \
postgres-check-v14 \
@@ -251,6 +302,12 @@ postgres-check: \
postgres-check-v16 \
postgres-check-v17
# This doesn't remove the effects of 'configure'.
.PHONY: clean
clean: postgres-clean neon-pg-clean-ext
$(MAKE) -C compute clean
$(CARGO_CMD_PREFIX) cargo clean
# This removes everything
.PHONY: distclean
distclean:
@@ -263,7 +320,7 @@ fmt:
postgres-%-pg-bsd-indent: postgres-%
+@echo "Compiling pg_bsd_indent"
$(MAKE) -C $(BUILD_DIR)/$*/src/tools/pg_bsd_indent/
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/src/tools/pg_bsd_indent/
# Create typedef list for the core. Note that generally it should be combined with
# buildfarm one to cover platform specific stuff.
@@ -282,7 +339,7 @@ postgres-%-pgindent: postgres-%-pg-bsd-indent postgres-%-typedefs.list
cat $(ROOT_PROJECT_DIR)/vendor/postgres-$*/src/tools/pgindent/typedefs.list |\
cat - postgres-$*-typedefs.list | sort | uniq > postgres-$*-typedefs-full.list
+@echo note: you might want to run it on selected files/dirs instead.
INDENT=$(BUILD_DIR)/$*/src/tools/pg_bsd_indent/pg_bsd_indent \
INDENT=$(POSTGRES_INSTALL_DIR)/build/$*/src/tools/pg_bsd_indent/pg_bsd_indent \
$(ROOT_PROJECT_DIR)/vendor/postgres-$*/src/tools/pgindent/pgindent --typedefs postgres-$*-typedefs-full.list \
$(ROOT_PROJECT_DIR)/vendor/postgres-$*/src/ \
--excludes $(ROOT_PROJECT_DIR)/vendor/postgres-$*/src/tools/pgindent/exclude_file_patterns
@@ -293,9 +350,9 @@ postgres-%-pgindent: postgres-%-pg-bsd-indent postgres-%-typedefs.list
neon-pgindent: postgres-v17-pg-bsd-indent neon-pg-ext-v17
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v17/bin/pg_config COPT='$(COPT)' \
FIND_TYPEDEF=$(ROOT_PROJECT_DIR)/vendor/postgres-v17/src/tools/find_typedef \
INDENT=$(BUILD_DIR)/v17/src/tools/pg_bsd_indent/pg_bsd_indent \
INDENT=$(POSTGRES_INSTALL_DIR)/build/v17/src/tools/pg_bsd_indent/pg_bsd_indent \
PGINDENT_SCRIPT=$(ROOT_PROJECT_DIR)/vendor/postgres-v17/src/tools/pgindent/pgindent \
-C $(BUILD_DIR)/neon-v17 \
-C $(POSTGRES_INSTALL_DIR)/build/neon-v17 \
-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile pgindent

View File

@@ -155,7 +155,7 @@ RUN set -e \
# Keep the version the same as in compute/compute-node.Dockerfile and
# test_runner/regress/test_compute_metrics.py.
ENV SQL_EXPORTER_VERSION=0.17.3
ENV SQL_EXPORTER_VERSION=0.17.0
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 \
@@ -292,7 +292,7 @@ WORKDIR /home/nonroot
# Rust
# Please keep the version of llvm (installed above) in sync with rust llvm (`rustc --version --verbose | grep LLVM`)
ENV RUSTC_VERSION=1.87.0
ENV RUSTC_VERSION=1.86.0
ENV RUSTUP_HOME="/home/nonroot/.rustup"
ENV PATH="/home/nonroot/.cargo/bin:${PATH}"
ARG RUSTFILT_VERSION=0.2.1
@@ -310,13 +310,13 @@ RUN curl -sSO https://static.rust-lang.org/rustup/dist/$(uname -m)-unknown-linux
. "$HOME/.cargo/env" && \
cargo --version && rustup --version && \
rustup component add llvm-tools rustfmt clippy && \
cargo install rustfilt --version ${RUSTFILT_VERSION} --locked && \
cargo install cargo-hakari --version ${CARGO_HAKARI_VERSION} --locked && \
cargo install cargo-deny --version ${CARGO_DENY_VERSION} --locked && \
cargo install cargo-hack --version ${CARGO_HACK_VERSION} --locked && \
cargo install cargo-nextest --version ${CARGO_NEXTEST_VERSION} --locked && \
cargo install cargo-chef --version ${CARGO_CHEF_VERSION} --locked && \
cargo install diesel_cli --version ${CARGO_DIESEL_CLI_VERSION} --locked \
cargo install rustfilt --version ${RUSTFILT_VERSION} && \
cargo install cargo-hakari --version ${CARGO_HAKARI_VERSION} && \
cargo install cargo-deny --locked --version ${CARGO_DENY_VERSION} && \
cargo install cargo-hack --version ${CARGO_HACK_VERSION} && \
cargo install cargo-nextest --version ${CARGO_NEXTEST_VERSION} && \
cargo install cargo-chef --locked --version ${CARGO_CHEF_VERSION} && \
cargo install diesel_cli --version ${CARGO_DIESEL_CLI_VERSION} \
--features postgres-bundled --no-default-features && \
rm -rf /home/nonroot/.cargo/registry && \
rm -rf /home/nonroot/.cargo/git

3
compute/.gitignore vendored
View File

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

View File

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

View File

@@ -77,6 +77,9 @@
# build_and_test.yml github workflow for how that's done.
ARG PG_VERSION
ARG REPOSITORY=ghcr.io/neondatabase
ARG IMAGE=build-tools
ARG TAG=pinned
ARG BUILD_TAG
ARG DEBIAN_VERSION=bookworm
ARG DEBIAN_FLAVOR=${DEBIAN_VERSION}-slim
@@ -146,11 +149,8 @@ RUN case $DEBIAN_VERSION in \
ninja-build git autoconf automake libtool build-essential bison flex libreadline-dev \
zlib1g-dev libxml2-dev libcurl4-openssl-dev libossp-uuid-dev wget ca-certificates pkg-config libssl-dev \
libicu-dev libxslt1-dev liblz4-dev libzstd-dev zstd curl unzip g++ \
libclang-dev \
jsonnet \
$VERSION_INSTALLS \
&& apt clean && rm -rf /var/lib/apt/lists/* && \
useradd -ms /bin/bash nonroot -b /home
&& apt clean && rm -rf /var/lib/apt/lists/*
#########################################################################################
#
@@ -171,6 +171,9 @@ RUN cd postgres && \
eval $CONFIGURE_CMD && \
make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s install && \
make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s -C contrib/ install && \
# Install headers
make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s -C src/include install && \
make MAKELEVEL=0 -j $(getconf _NPROCESSORS_ONLN) -s -C src/interfaces/libpq install && \
# Enable some of contrib extensions
echo 'trusted = true' >> /usr/local/pgsql/share/extension/autoinc.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/dblink.control && \
@@ -294,7 +297,6 @@ RUN ./autogen.sh && \
./configure --with-sfcgal=/usr/local/bin/sfcgal-config && \
make -j $(getconf _NPROCESSORS_ONLN) && \
make -j $(getconf _NPROCESSORS_ONLN) install && \
make staged-install && \
cd extensions/postgis && \
make clean && \
make -j $(getconf _NPROCESSORS_ONLN) install && \
@@ -580,38 +582,6 @@ RUN make -j $(getconf _NPROCESSORS_ONLN) && \
make -j $(getconf _NPROCESSORS_ONLN) install && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/hypopg.control
#########################################################################################
#
# Layer "online_advisor-build"
# compile online_advisor extension
#
#########################################################################################
FROM build-deps AS online_advisor-src
ARG PG_VERSION
# online_advisor supports all Postgres version starting from PG14, but prior to PG17 has to be included in preload_shared_libraries
# last release 1.0 - May 15, 2025
WORKDIR /ext-src
RUN case "${PG_VERSION:?}" in \
"v17") \
;; \
*) \
echo "skipping the version of online_advistor for $PG_VERSION" && exit 0 \
;; \
esac && \
wget https://github.com/knizhnik/online_advisor/archive/refs/tags/1.0.tar.gz -O online_advisor.tar.gz && \
echo "37dcadf8f7cc8d6cc1f8831276ee245b44f1b0274f09e511e47a67738ba9ed0f online_advisor.tar.gz" | sha256sum --check && \
mkdir online_advisor-src && cd online_advisor-src && tar xzf ../online_advisor.tar.gz --strip-components=1 -C .
FROM pg-build AS online_advisor-build
COPY --from=online_advisor-src /ext-src/ /ext-src/
WORKDIR /ext-src/
RUN if [ -d online_advisor-src ]; then \
cd online_advisor-src && \
make -j install && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/online_advisor.control; \
fi
#########################################################################################
#
# Layer "pg_hashids-build"
@@ -1054,10 +1024,17 @@ RUN make -j $(getconf _NPROCESSORS_ONLN) && \
#########################################################################################
#
# Layer "build-deps with Rust toolchain installed"
# Layer "pg build with nonroot user and cargo installed"
# This layer is base and common for layers with `pgrx`
#
#########################################################################################
FROM build-deps AS build-deps-with-cargo
FROM pg-build AS pg-build-nonroot-with-cargo
ARG PG_VERSION
RUN apt update && \
apt install --no-install-recommends --no-install-suggests -y curl libclang-dev && \
apt clean && rm -rf /var/lib/apt/lists/* && \
useradd -ms /bin/bash nonroot -b /home
ENV HOME=/home/nonroot
ENV PATH="/home/nonroot/.cargo/bin:$PATH"
@@ -1072,29 +1049,13 @@ RUN curl -sSO https://static.rust-lang.org/rustup/dist/$(uname -m)-unknown-linux
./rustup-init -y --no-modify-path --profile minimal --default-toolchain stable && \
rm rustup-init
#########################################################################################
#
# Layer "pg-build with Rust toolchain installed"
# This layer is base and common for layers with `pgrx`
#
#########################################################################################
FROM pg-build AS pg-build-with-cargo
ARG PG_VERSION
ENV HOME=/home/nonroot
ENV PATH="/home/nonroot/.cargo/bin:$PATH"
USER nonroot
WORKDIR /home/nonroot
COPY --from=build-deps-with-cargo /home/nonroot /home/nonroot
#########################################################################################
#
# Layer "rust extensions"
# This layer is used to build `pgrx` deps
#
#########################################################################################
FROM pg-build-with-cargo AS rust-extensions-build
FROM pg-build-nonroot-with-cargo AS rust-extensions-build
ARG PG_VERSION
RUN case "${PG_VERSION:?}" in \
@@ -1116,7 +1077,7 @@ USER root
# and eventually get merged with `rust-extensions-build`
#
#########################################################################################
FROM pg-build-with-cargo AS rust-extensions-build-pgrx12
FROM pg-build-nonroot-with-cargo AS rust-extensions-build-pgrx12
ARG PG_VERSION
RUN cargo install --locked --version 0.12.9 cargo-pgrx && \
@@ -1124,23 +1085,6 @@ RUN cargo install --locked --version 0.12.9 cargo-pgrx && \
USER root
#########################################################################################
#
# Layer "rust extensions pgrx14"
#
# Version 14 is now required by a few
# This layer should be used as a base for new pgrx extensions,
# and eventually get merged with `rust-extensions-build`
#
#########################################################################################
FROM pg-build-with-cargo AS rust-extensions-build-pgrx14
ARG PG_VERSION
RUN cargo install --locked --version 0.14.1 cargo-pgrx && \
/bin/bash -c 'cargo pgrx init --pg${PG_VERSION:1}=/usr/local/pgsql/bin/pg_config'
USER root
#########################################################################################
#
# Layers "pg-onnx-build" and "pgrag-build"
@@ -1150,19 +1094,17 @@ USER root
FROM build-deps AS pgrag-src
ARG PG_VERSION
WORKDIR /ext-src
COPY compute/patches/onnxruntime.patch .
WORKDIR /ext-src
RUN wget https://github.com/microsoft/onnxruntime/archive/refs/tags/v1.18.1.tar.gz -O onnxruntime.tar.gz && \
mkdir onnxruntime-src && cd onnxruntime-src && tar xzf ../onnxruntime.tar.gz --strip-components=1 -C . && \
patch -p1 < /ext-src/onnxruntime.patch && \
echo "#nothing to test here" > neon-test.sh
RUN wget https://github.com/neondatabase-labs/pgrag/archive/refs/tags/v0.1.2.tar.gz -O pgrag.tar.gz && \
echo "7361654ea24f08cbb9db13c2ee1c0fe008f6114076401bb871619690dafc5225 pgrag.tar.gz" | sha256sum --check && \
RUN wget https://github.com/neondatabase-labs/pgrag/archive/refs/tags/v0.0.0.tar.gz -O pgrag.tar.gz && \
echo "2cbe394c1e74fc8bcad9b52d5fbbfb783aef834ca3ce44626cfd770573700bb4 pgrag.tar.gz" | sha256sum --check && \
mkdir pgrag-src && cd pgrag-src && tar xzf ../pgrag.tar.gz --strip-components=1 -C .
FROM rust-extensions-build-pgrx14 AS pgrag-build
FROM rust-extensions-build-pgrx12 AS pgrag-build
COPY --from=pgrag-src /ext-src/ /ext-src/
# Install build-time dependencies
@@ -1182,21 +1124,21 @@ RUN . venv/bin/activate && \
WORKDIR /ext-src/pgrag-src
RUN cd exts/rag && \
sed -i 's/pgrx = "0.14.1"/pgrx = { version = "0.14.1", features = [ "unsafe-postgres" ] }/g' Cargo.toml && \
sed -i 's/pgrx = "0.12.6"/pgrx = { version = "0.12.9", features = [ "unsafe-postgres" ] }/g' Cargo.toml && \
cargo pgrx install --release && \
echo "trusted = true" >> /usr/local/pgsql/share/extension/rag.control
RUN cd exts/rag_bge_small_en_v15 && \
sed -i 's/pgrx = "0.14.1"/pgrx = { version = "0.14.1", features = [ "unsafe-postgres" ] }/g' Cargo.toml && \
sed -i 's/pgrx = "0.12.6"/pgrx = { version = "0.12.9", features = [ "unsafe-postgres" ] }/g' Cargo.toml && \
ORT_LIB_LOCATION=/ext-src/onnxruntime-src/build/Linux \
REMOTE_ONNX_URL=http://pg-ext-s3-gateway.pg-ext-s3-gateway.svc.cluster.local/pgrag-data/bge_small_en_v15.onnx \
REMOTE_ONNX_URL=http://pg-ext-s3-gateway/pgrag-data/bge_small_en_v15.onnx \
cargo pgrx install --release --features remote_onnx && \
echo "trusted = true" >> /usr/local/pgsql/share/extension/rag_bge_small_en_v15.control
RUN cd exts/rag_jina_reranker_v1_tiny_en && \
sed -i 's/pgrx = "0.14.1"/pgrx = { version = "0.14.1", features = [ "unsafe-postgres" ] }/g' Cargo.toml && \
sed -i 's/pgrx = "0.12.6"/pgrx = { version = "0.12.9", features = [ "unsafe-postgres" ] }/g' Cargo.toml && \
ORT_LIB_LOCATION=/ext-src/onnxruntime-src/build/Linux \
REMOTE_ONNX_URL=http://pg-ext-s3-gateway.pg-ext-s3-gateway.svc.cluster.local/pgrag-data/jina_reranker_v1_tiny_en.onnx \
REMOTE_ONNX_URL=http://pg-ext-s3-gateway/pgrag-data/jina_reranker_v1_tiny_en.onnx \
cargo pgrx install --release --features remote_onnx && \
echo "trusted = true" >> /usr/local/pgsql/share/extension/rag_jina_reranker_v1_tiny_en.control
@@ -1363,8 +1305,8 @@ ARG PG_VERSION
# Do not update without approve from proxy team
# Make sure the version is reflected in proxy/src/serverless/local_conn_pool.rs
WORKDIR /ext-src
RUN wget https://github.com/neondatabase/pg_session_jwt/archive/refs/tags/v0.3.1.tar.gz -O pg_session_jwt.tar.gz && \
echo "62fec9e472cb805c53ba24a0765afdb8ea2720cfc03ae7813e61687b36d1b0ad pg_session_jwt.tar.gz" | sha256sum --check && \
RUN wget https://github.com/neondatabase/pg_session_jwt/archive/refs/tags/v0.3.0.tar.gz -O pg_session_jwt.tar.gz && \
echo "19be2dc0b3834d643706ed430af998bb4c2cdf24b3c45e7b102bb3a550e8660c pg_session_jwt.tar.gz" | sha256sum --check && \
mkdir pg_session_jwt-src && cd pg_session_jwt-src && tar xzf ../pg_session_jwt.tar.gz --strip-components=1 -C . && \
sed -i 's/pgrx = "0.12.6"/pgrx = { version = "0.12.9", features = [ "unsafe-postgres" ] }/g' Cargo.toml && \
sed -i 's/version = "0.12.6"/version = "0.12.9"/g' pgrx-tests/Cargo.toml && \
@@ -1377,40 +1319,6 @@ COPY --from=pg_session_jwt-src /ext-src/ /ext-src/
WORKDIR /ext-src/pg_session_jwt-src
RUN cargo pgrx install --release
#########################################################################################
#
# Layer "pg-anon-pg-build"
# compile anon extension
#
#########################################################################################
FROM pg-build AS pg_anon-src
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
WORKDIR /ext-src
COPY compute/patches/anon_v2.patch .
# This is an experimental extension, never got to real production.
# !Do not remove! It can be present in shared_preload_libraries and compute will fail to start if library is not found.
ENV PATH="/usr/local/pgsql/bin/:$PATH"
RUN wget https://gitlab.com/dalibo/postgresql_anonymizer/-/archive/2.1.0/postgresql_anonymizer-latest.tar.gz -O pg_anon.tar.gz && \
echo "48e7f5ae2f1ca516df3da86c5c739d48dd780a4e885705704ccaad0faa89d6c0 pg_anon.tar.gz" | sha256sum --check && \
mkdir pg_anon-src && cd pg_anon-src && tar xzf ../pg_anon.tar.gz --strip-components=1 -C . && \
find /usr/local/pgsql -type f | sed 's|^/usr/local/pgsql/||' > /before.txt && \
sed -i 's/pgrx = "0.14.1"/pgrx = { version = "=0.14.1", features = [ "unsafe-postgres" ] }/g' Cargo.toml && \
patch -p1 < /ext-src/anon_v2.patch
FROM rust-extensions-build-pgrx14 AS pg-anon-pg-build
ARG PG_VERSION
COPY --from=pg_anon-src /ext-src/ /ext-src/
WORKDIR /ext-src
RUN cd pg_anon-src && \
make -j $(getconf _NPROCESSORS_ONLN) extension PG_CONFIG=/usr/local/pgsql/bin/pg_config PGVER=pg$(echo "$PG_VERSION" | sed 's/^v//') && \
make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config PGVER=pg$(echo "$PG_VERSION" | sed 's/^v//') && \
chmod -R a+r ../pg_anon-src && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/anon.control;
########################################################################################
#########################################################################################
#
# Layer "wal2json-build"
@@ -1565,20 +1473,20 @@ ARG PG_VERSION
WORKDIR /ext-src
RUN case "${PG_VERSION}" in \
"v14") \
export PGAUDIT_VERSION=1.6.3 \
export PGAUDIT_CHECKSUM=37a8f5a7cc8d9188e536d15cf0fdc457fcdab2547caedb54442c37f124110919 \
export PGAUDIT_VERSION=1.6.2 \
export PGAUDIT_CHECKSUM=1f350d70a0cbf488c0f2b485e3a5c9b11f78ad9e3cbb95ef6904afa1eb3187eb \
;; \
"v15") \
export PGAUDIT_VERSION=1.7.1 \
export PGAUDIT_CHECKSUM=e9c8e6e092d82b2f901d72555ce0fe7780552f35f8985573796cd7e64b09d4ec \
export PGAUDIT_VERSION=1.7.0 \
export PGAUDIT_CHECKSUM=8f4a73e451c88c567e516e6cba7dc1e23bc91686bb6f1f77f8f3126d428a8bd8 \
;; \
"v16") \
export PGAUDIT_VERSION=16.1 \
export PGAUDIT_CHECKSUM=3bae908ab70ba0c6f51224009dbcfff1a97bd6104c6273297a64292e1b921fee \
export PGAUDIT_VERSION=16.0 \
export PGAUDIT_CHECKSUM=d53ef985f2d0b15ba25c512c4ce967dce07b94fd4422c95bd04c4c1a055fe738 \
;; \
"v17") \
export PGAUDIT_VERSION=17.1 \
export PGAUDIT_CHECKSUM=9c5f37504d393486cc75d2ced83f75f5899be64fa85f689d6babb833b4361e6c \
export PGAUDIT_VERSION=17.0 \
export PGAUDIT_CHECKSUM=7d0d08d030275d525f36cd48b38c6455f1023da863385badff0cec44965bfd8c \
;; \
*) \
echo "pgaudit is not supported on this PostgreSQL version" && exit 1;; \
@@ -1629,7 +1537,18 @@ FROM pg-build AS neon-ext-build
ARG PG_VERSION
COPY pgxn/ pgxn/
RUN make -j $(getconf _NPROCESSORS_ONLN) -C pgxn -s install-compute
RUN make -j $(getconf _NPROCESSORS_ONLN) \
-C pgxn/neon \
-s install && \
make -j $(getconf _NPROCESSORS_ONLN) \
-C pgxn/neon_utils \
-s install && \
make -j $(getconf _NPROCESSORS_ONLN) \
-C pgxn/neon_test_utils \
-s install && \
make -j $(getconf _NPROCESSORS_ONLN) \
-C pgxn/neon_rmgr \
-s install
#########################################################################################
#
@@ -1678,7 +1597,6 @@ COPY --from=pg_jsonschema-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=pg_graphql-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=pg_tiktoken-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=hypopg-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=online_advisor-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=pg_hashids-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=rum-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=pgtap-build /usr/local/pgsql/ /usr/local/pgsql/
@@ -1697,7 +1615,6 @@ COPY --from=pg_uuidv7-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=pg_roaringbitmap-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=pg_semver-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=wal2json-build /usr/local/pgsql /usr/local/pgsql
COPY --from=pg-anon-pg-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=pg_ivm-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=pg_partman-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=pg_mooncake-build /usr/local/pgsql/ /usr/local/pgsql/
@@ -1719,7 +1636,7 @@ FROM extensions-${EXTENSIONS} AS neon-pg-ext-build
# Compile the Neon-specific `compute_ctl`, `fast_import`, and `local_proxy` binaries
#
#########################################################################################
FROM build-deps-with-cargo AS compute-tools
FROM $REPOSITORY/$IMAGE:$TAG AS compute-tools
ARG BUILD_TAG
ENV BUILD_TAG=$BUILD_TAG
@@ -1729,7 +1646,7 @@ COPY --chown=nonroot . .
RUN --mount=type=cache,uid=1000,target=/home/nonroot/.cargo/registry \
--mount=type=cache,uid=1000,target=/home/nonroot/.cargo/git \
--mount=type=cache,uid=1000,target=/home/nonroot/target \
cargo build --locked --profile release-line-debug-size-lto --bin compute_ctl --bin fast_import --bin local_proxy && \
mold -run cargo build --locked --profile release-line-debug-size-lto --bin compute_ctl --bin fast_import --bin local_proxy && \
mkdir target-bin && \
cp target/release-line-debug-size-lto/compute_ctl \
target/release-line-debug-size-lto/fast_import \
@@ -1782,17 +1699,17 @@ ARG TARGETARCH
RUN if [ "$TARGETARCH" = "amd64" ]; then\
postgres_exporter_sha256='59aa4a7bb0f7d361f5e05732f5ed8c03cc08f78449cef5856eadec33a627694b';\
pgbouncer_exporter_sha256='c9f7cf8dcff44f0472057e9bf52613d93f3ffbc381ad7547a959daa63c5e84ac';\
sql_exporter_sha256='9a41127a493e8bfebfe692bf78c7ed2872a58a3f961ee534d1b0da9ae584aaab';\
sql_exporter_sha256='38e439732bbf6e28ca4a94d7bc3686d3fa1abdb0050773d5617a9efdb9e64d08';\
else\
postgres_exporter_sha256='d1dedea97f56c6d965837bfd1fbb3e35a3b4a4556f8cccee8bd513d8ee086124';\
pgbouncer_exporter_sha256='217c4afd7e6492ae904055bc14fe603552cf9bac458c063407e991d68c519da3';\
sql_exporter_sha256='530e6afc77c043497ed965532c4c9dfa873bc2a4f0b3047fad367715c0081d6a';\
sql_exporter_sha256='11918b00be6e2c3a67564adfdb2414fdcbb15a5db76ea17d1d1a944237a893c6';\
fi\
&& curl -sL https://github.com/prometheus-community/postgres_exporter/releases/download/v0.17.1/postgres_exporter-0.17.1.linux-${TARGETARCH}.tar.gz\
| tar xzf - --strip-components=1 -C.\
&& curl -sL https://github.com/prometheus-community/pgbouncer_exporter/releases/download/v0.10.2/pgbouncer_exporter-0.10.2.linux-${TARGETARCH}.tar.gz\
| tar xzf - --strip-components=1 -C.\
&& curl -sL https://github.com/burningalchemist/sql_exporter/releases/download/0.17.3/sql_exporter-0.17.3.linux-${TARGETARCH}.tar.gz\
&& curl -sL https://github.com/burningalchemist/sql_exporter/releases/download/0.17.0/sql_exporter-0.17.0.linux-${TARGETARCH}.tar.gz\
| tar xzf - --strip-components=1 -C.\
&& echo "${postgres_exporter_sha256} postgres_exporter" | sha256sum -c -\
&& echo "${pgbouncer_exporter_sha256} pgbouncer_exporter" | sha256sum -c -\
@@ -1823,11 +1740,10 @@ RUN rm /usr/local/pgsql/lib/lib*.a
# Preprocess the sql_exporter configuration files
#
#########################################################################################
FROM build-deps AS sql_exporter_preprocessor
FROM $REPOSITORY/$IMAGE:$TAG AS sql_exporter_preprocessor
ARG PG_VERSION
USER nonroot
WORKDIR /home/nonroot
COPY --chown=nonroot compute compute
@@ -1841,27 +1757,12 @@ RUN make PG_VERSION="${PG_VERSION:?}" -C compute
FROM pg-build AS extension-tests
ARG PG_VERSION
# This is required for the PostGIS test
RUN apt-get update && case $DEBIAN_VERSION in \
bullseye) \
apt-get install -y libproj19 libgdal28 time; \
;; \
bookworm) \
apt-get install -y libgdal32 libproj25 time; \
;; \
*) \
echo "Unknown Debian version ${DEBIAN_VERSION}" && exit 1 \
;; \
esac
COPY docker-compose/ext-src/ /ext-src/
COPY --from=pg-build /postgres /postgres
COPY --from=postgis-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=postgis-build /ext-src/postgis-src /ext-src/postgis-src
COPY --from=postgis-build /sfcgal/* /usr
#COPY --from=postgis-src /ext-src/ /ext-src/
COPY --from=plv8-src /ext-src/ /ext-src/
COPY --from=h3-pg-src /ext-src/h3-pg-src /ext-src/h3-pg-src
#COPY --from=h3-pg-src /ext-src/ /ext-src/
COPY --from=postgresql-unit-src /ext-src/ /ext-src/
COPY --from=pgvector-src /ext-src/ /ext-src/
COPY --from=pgjwt-src /ext-src/ /ext-src/
@@ -1870,7 +1771,6 @@ COPY --from=pgjwt-src /ext-src/ /ext-src/
COPY --from=pg_graphql-src /ext-src/ /ext-src/
#COPY --from=pg_tiktoken-src /ext-src/ /ext-src/
COPY --from=hypopg-src /ext-src/ /ext-src/
COPY --from=online_advisor-src /ext-src/ /ext-src/
COPY --from=pg_hashids-src /ext-src/ /ext-src/
COPY --from=rum-src /ext-src/ /ext-src/
COPY --from=pgtap-src /ext-src/ /ext-src/
@@ -1900,9 +1800,8 @@ COPY compute/patches/pg_repack.patch /ext-src
RUN cd /ext-src/pg_repack-src && patch -p1 </ext-src/pg_repack.patch && rm -f /ext-src/pg_repack.patch
COPY --chmod=755 docker-compose/run-tests.sh /run-tests.sh
RUN echo /usr/local/pgsql/lib > /etc/ld.so.conf.d/00-neon.conf && /sbin/ldconfig
RUN apt-get update && apt-get install -y libtap-parser-sourcehandler-pgtap-perl jq \
&& apt clean && rm -rf /ext-src/*.tar.gz /ext-src/*.patch /var/lib/apt/lists/*
RUN apt-get update && apt-get install -y libtap-parser-sourcehandler-pgtap-perl\
&& apt clean && rm -rf /ext-src/*.tar.gz /var/lib/apt/lists/*
ENV PATH=/usr/local/pgsql/bin:$PATH
ENV PGHOST=compute
ENV PGPORT=55433
@@ -2020,8 +1919,7 @@ COPY --from=sql_exporter_preprocessor --chmod=0644 /home/nonroot/compute/etc/sql
COPY --from=sql_exporter_preprocessor --chmod=0644 /home/nonroot/compute/etc/neon_collector_autoscaling.yml /etc/neon_collector_autoscaling.yml
# Make the libraries we built available
COPY --chmod=0666 compute/etc/ld.so.conf.d/00-neon.conf /etc/ld.so.conf.d/00-neon.conf
RUN /sbin/ldconfig
RUN echo '/usr/local/lib' >> /etc/ld.so.conf && /sbin/ldconfig
# rsyslog config permissions
# directory for rsyslogd pid file

View File

@@ -1 +0,0 @@
/usr/local/lib

View File

@@ -23,8 +23,6 @@
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/compute_getpage_stuck_requests_total.libsonnet',
import 'sql_exporter/compute_getpage_max_inflight_stuck_time_ms.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',

View File

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

View File

@@ -1,9 +0,0 @@
{
metric_name: 'compute_getpage_max_inflight_stuck_time_ms',
type: 'gauge',
help: 'Max wait time for stuck requests among all backends. Includes only active stuck requests, terminated or disconnected ones are not accounted for',
values: [
'compute_getpage_max_inflight_stuck_time_ms',
],
query_ref: 'neon_perf_counters',
}

View File

@@ -1,9 +0,0 @@
{
metric_name: 'compute_getpage_stuck_requests_total',
type: 'counter',
help: 'Total number of Getpage requests left without an answer for more than pageserver_response_log_timeout but less than pageserver_response_disconnect_timeout',
values: [
'compute_getpage_stuck_requests_total',
],
query_ref: 'neon_perf_counters',
}

View File

@@ -9,8 +9,6 @@ SELECT d.* FROM pg_catalog.jsonb_to_record((SELECT jb FROM c)) AS d(
getpage_wait_seconds_sum numeric,
getpage_prefetch_requests_total numeric,
getpage_sync_requests_total numeric,
compute_getpage_stuck_requests_total numeric,
compute_getpage_max_inflight_stuck_time_ms numeric,
getpage_prefetch_misses_total numeric,
getpage_prefetch_discards_total numeric,
getpage_prefetches_buffered numeric,

View File

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

View File

@@ -1,121 +0,0 @@
pg_settings:
# Common settings for primaries and replicas of all versions.
common:
# Check for client disconnection every 1 minute. By default, Postgres will detect the
# loss of the connection only at the next interaction with the socket, when it waits
# for, receives or sends data, so it will likely waste resources till the end of the
# query execution. There should be no drawbacks in setting this for everyone, so enable
# it by default. If anyone will complain, we can allow editing it.
# https://www.postgresql.org/docs/16/runtime-config-connection.html#GUC-CLIENT-CONNECTION-CHECK-INTERVAL
client_connection_check_interval: "60000" # 1 minute
# ---- IO ----
effective_io_concurrency: "20"
maintenance_io_concurrency: "100"
fsync: "off"
hot_standby: "off"
# We allow users to change this if needed, but by default we
# just don't want to see long-lasting idle transactions, as they
# prevent activity monitor from suspending projects.
idle_in_transaction_session_timeout: "300000" # 5 minutes
listen_addresses: "*"
# --- LOGGING ---- helps investigations
log_connections: "on"
log_disconnections: "on"
# 1GB, unit is KB
log_temp_files: "1048576"
# Disable dumping customer data to logs, both to increase data privacy
# and to reduce the amount the logs.
log_error_verbosity: "terse"
log_min_error_statement: "panic"
max_connections: "100"
# --- WAL ---
# - flush lag is the max amount of WAL that has been generated but not yet stored
# to disk in the page server. A smaller value means less delay after a pageserver
# restart, but if you set it too small you might again need to slow down writes if the
# pageserver cannot flush incoming WAL to disk fast enough. This must be larger
# than the pageserver's checkpoint interval, currently 1 GB! Otherwise you get a
# a deadlock where the compute node refuses to generate more WAL before the
# old WAL has been uploaded to S3, but the pageserver is waiting for more WAL
# to be generated before it is uploaded to S3.
max_replication_flush_lag: "10GB"
max_replication_slots: "10"
# Backpressure configuration:
# - write lag is the max amount of WAL that has been generated by Postgres but not yet
# processed by the page server. Making this smaller reduces the worst case latency
# of a GetPage request, if you request a page that was recently modified. On the other
# hand, if this is too small, the compute node might need to wait on a write if there is a
# hiccup in the network or page server so that the page server has temporarily fallen
# behind.
#
# Previously it was set to 500 MB, but it caused compute being unresponsive under load
# https://github.com/neondatabase/neon/issues/2028
max_replication_write_lag: "500MB"
max_wal_senders: "10"
# A Postgres checkpoint is cheap in storage, as doesn't involve any significant amount
# of real I/O. Only the SLRU buffers and some other small files are flushed to disk.
# However, as long as we have full_page_writes=on, page updates after a checkpoint
# include full-page images which bloats the WAL. So may want to bump max_wal_size to
# reduce the WAL bloating, but at the same it will increase pg_wal directory size on
# compute and can lead to out of disk error on k8s nodes.
max_wal_size: "1024"
wal_keep_size: "0"
wal_level: "replica"
# Reduce amount of WAL generated by default.
wal_log_hints: "off"
# - without wal_sender_timeout set we don't get feedback messages,
# required for backpressure.
wal_sender_timeout: "10000"
# We have some experimental extensions, which we don't want users to install unconsciously.
# To install them, users would need to set the `neon.allow_unstable_extensions` setting.
# There are two of them currently:
# - `pgrag` - https://github.com/neondatabase-labs/pgrag - extension is actually called just `rag`,
# and two dependencies:
# - `rag_bge_small_en_v15`
# - `rag_jina_reranker_v1_tiny_en`
# - `pg_mooncake` - https://github.com/Mooncake-Labs/pg_mooncake/
neon.unstable_extensions: "rag,rag_bge_small_en_v15,rag_jina_reranker_v1_tiny_en,pg_mooncake,anon"
neon.protocol_version: "3"
password_encryption: "scram-sha-256"
# This is important to prevent Postgres from trying to perform
# a local WAL redo after backend crash. It should exit and let
# the systemd or k8s to do a fresh startup with compute_ctl.
restart_after_crash: "off"
# By default 3. We have the following persistent connections in the VM:
# * compute_activity_monitor (from compute_ctl)
# * postgres-exporter (metrics collector; it has 2 connections)
# * sql_exporter (metrics collector; we have 2 instances [1 for us & users; 1 for autoscaling])
# * vm-monitor (to query & change file cache size)
# i.e. total of 6. Let's reserve 7, so there's still at least one left over.
superuser_reserved_connections: "7"
synchronous_standby_names: "walproposer"
replica:
hot_standby: "on"
per_version:
17:
common:
# PostgreSQL 17 has a new IO system called "read stream", which can combine IOs up to some
# size. It still has some issues with readahead, though, so we default to disabled/
# "no combining of IOs" to make sure we get the maximum prefetch depth.
# See also: https://github.com/neondatabase/neon/pull/9860
io_combine_limit: "1"
replica:
# prefetching of blocks referenced in WAL doesn't make sense for us
# Neon hot standby ignores pages that are not in the shared_buffers
recovery_prefetch: "off"
16:
common: {}
replica:
# prefetching of blocks referenced in WAL doesn't make sense for us
# Neon hot standby ignores pages that are not in the shared_buffers
recovery_prefetch: "off"
15:
common: {}
replica:
# prefetching of blocks referenced in WAL doesn't make sense for us
# Neon hot standby ignores pages that are not in the shared_buffers
recovery_prefetch: "off"
14:
common: {}
replica: {}

View File

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

View File

@@ -1,7 +0,0 @@
{
"name": "neon-compute",
"private": true,
"dependencies": {
"@sourcemeta/jsonschema": "9.3.4"
}
}

View File

@@ -1,129 +0,0 @@
diff --git a/sql/anon.sql b/sql/anon.sql
index 0cdc769..f6cc950 100644
--- a/sql/anon.sql
+++ b/sql/anon.sql
@@ -1141,3 +1141,8 @@ $$
-- TODO : https://en.wikipedia.org/wiki/L-diversity
-- TODO : https://en.wikipedia.org/wiki/T-closeness
+
+-- NEON Patches
+
+GRANT ALL ON SCHEMA anon to neon_superuser;
+GRANT ALL ON ALL TABLES IN SCHEMA anon TO neon_superuser;
diff --git a/sql/init.sql b/sql/init.sql
index 7da6553..9b6164b 100644
--- a/sql/init.sql
+++ b/sql/init.sql
@@ -74,50 +74,49 @@ $$
SECURITY LABEL FOR anon ON FUNCTION anon.load_csv IS 'UNTRUSTED';
--- load fake data from a given path
-CREATE OR REPLACE FUNCTION anon.init(
- datapath TEXT
-)
+CREATE OR REPLACE FUNCTION anon.load_fake_data()
RETURNS BOOLEAN
AS $$
DECLARE
- datapath_check TEXT;
success BOOLEAN;
+ sharedir TEXT;
+ datapath TEXT;
BEGIN
- IF anon.is_initialized() THEN
- RAISE NOTICE 'The anon extension is already initialized.';
- RETURN TRUE;
- END IF;
+ datapath := '/extension/anon/';
+ -- find the local extension directory
+ SELECT setting INTO sharedir
+ FROM pg_catalog.pg_config
+ WHERE name = 'SHAREDIR';
SELECT bool_or(results) INTO success
FROM unnest(array[
- anon.load_csv('anon.identifiers_category',datapath||'/identifiers_category.csv'),
- anon.load_csv('anon.identifier',datapath ||'/identifier.csv'),
- anon.load_csv('anon.address',datapath ||'/address.csv'),
- anon.load_csv('anon.city',datapath ||'/city.csv'),
- anon.load_csv('anon.company',datapath ||'/company.csv'),
- anon.load_csv('anon.country',datapath ||'/country.csv'),
- anon.load_csv('anon.email', datapath ||'/email.csv'),
- anon.load_csv('anon.first_name',datapath ||'/first_name.csv'),
- anon.load_csv('anon.iban',datapath ||'/iban.csv'),
- anon.load_csv('anon.last_name',datapath ||'/last_name.csv'),
- anon.load_csv('anon.postcode',datapath ||'/postcode.csv'),
- anon.load_csv('anon.siret',datapath ||'/siret.csv'),
- anon.load_csv('anon.lorem_ipsum',datapath ||'/lorem_ipsum.csv')
+ anon.load_csv('anon.identifiers_category',sharedir || datapath || '/identifiers_category.csv'),
+ anon.load_csv('anon.identifier',sharedir || datapath || '/identifier.csv'),
+ anon.load_csv('anon.address',sharedir || datapath || '/address.csv'),
+ anon.load_csv('anon.city',sharedir || datapath || '/city.csv'),
+ anon.load_csv('anon.company',sharedir || datapath || '/company.csv'),
+ anon.load_csv('anon.country',sharedir || datapath || '/country.csv'),
+ anon.load_csv('anon.email', sharedir || datapath || '/email.csv'),
+ anon.load_csv('anon.first_name',sharedir || datapath || '/first_name.csv'),
+ anon.load_csv('anon.iban',sharedir || datapath || '/iban.csv'),
+ anon.load_csv('anon.last_name',sharedir || datapath || '/last_name.csv'),
+ anon.load_csv('anon.postcode',sharedir || datapath || '/postcode.csv'),
+ anon.load_csv('anon.siret',sharedir || datapath || '/siret.csv'),
+ anon.load_csv('anon.lorem_ipsum',sharedir || datapath || '/lorem_ipsum.csv')
]) results;
RETURN success;
-
END;
$$
- LANGUAGE PLPGSQL
+ LANGUAGE plpgsql
VOLATILE
RETURNS NULL ON NULL INPUT
- PARALLEL UNSAFE -- because load_csv is unsafe
- SECURITY INVOKER
+ PARALLEL UNSAFE -- because of the EXCEPTION
+ SECURITY DEFINER
SET search_path=''
;
-SECURITY LABEL FOR anon ON FUNCTION anon.init(TEXT) IS 'UNTRUSTED';
+
+SECURITY LABEL FOR anon ON FUNCTION anon.load_fake_data IS 'UNTRUSTED';
-- People tend to forget the anon.init() step
-- This is a friendly notice for them
@@ -144,7 +143,7 @@ SECURITY LABEL FOR anon ON FUNCTION anon.notice_if_not_init IS 'UNTRUSTED';
CREATE OR REPLACE FUNCTION anon.load(TEXT)
RETURNS BOOLEAN AS
$$
- SELECT anon.init($1);
+ SELECT anon.init();
$$
LANGUAGE SQL
VOLATILE
@@ -159,16 +158,16 @@ SECURITY LABEL FOR anon ON FUNCTION anon.load(TEXT) IS 'UNTRUSTED';
CREATE OR REPLACE FUNCTION anon.init()
RETURNS BOOLEAN
AS $$
- WITH conf AS (
- -- find the local extension directory
- SELECT setting AS sharedir
- FROM pg_catalog.pg_config
- WHERE name = 'SHAREDIR'
- )
- SELECT anon.init(conf.sharedir || '/extension/anon/')
- FROM conf;
+BEGIN
+ IF anon.is_initialized() THEN
+ RAISE NOTICE 'The anon extension is already initialized.';
+ RETURN TRUE;
+ END IF;
+
+ RETURN anon.load_fake_data();
+END;
$$
- LANGUAGE SQL
+ LANGUAGE plpgsql
VOLATILE
PARALLEL UNSAFE -- because init is unsafe
SECURITY INVOKER

View File

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

View File

@@ -7,7 +7,7 @@ index 255e616..1c6edb7 100644
RelationGetRelationName(index));
+#ifdef NEON_SMGR
+ smgr_start_unlogged_build(RelationGetSmgr(index));
+ smgr_start_unlogged_build(index->rd_smgr);
+#endif
+
initRumState(&buildstate.rumstate, index);
@@ -18,7 +18,7 @@ index 255e616..1c6edb7 100644
rumUpdateStats(index, &buildstate.buildStats, buildstate.rumstate.isBuild);
+#ifdef NEON_SMGR
+ smgr_finish_unlogged_build_phase_1(RelationGetSmgr(index));
+ smgr_finish_unlogged_build_phase_1(index->rd_smgr);
+#endif
+
/*
@@ -29,7 +29,7 @@ index 255e616..1c6edb7 100644
}
+#ifdef NEON_SMGR
+ smgr_end_unlogged_build(RelationGetSmgr(index));
+ smgr_end_unlogged_build(index->rd_smgr);
+#endif
+
/*

View File

@@ -22,11 +22,11 @@ commands:
- name: local_proxy
user: postgres
sysvInitAction: respawn
shell: 'RUST_LOG="error" /usr/local/bin/local_proxy --config-path /etc/local_proxy/config.json --pid-path /etc/local_proxy/pid --http 0.0.0.0:10432'
shell: 'RUST_LOG="info,proxy::serverless::sql_over_http=warn" /usr/local/bin/local_proxy --config-path /etc/local_proxy/config.json --pid-path /etc/local_proxy/pid --http 0.0.0.0:10432'
- name: postgres-exporter
user: nobody
sysvInitAction: respawn
shell: 'DATA_SOURCE_NAME="user=cloud_admin sslmode=disable dbname=postgres application_name=postgres-exporter pgaudit.log=none" /bin/postgres_exporter --config.file=/etc/postgres_exporter.yml'
shell: 'DATA_SOURCE_NAME="user=cloud_admin sslmode=disable dbname=postgres application_name=postgres-exporter" /bin/postgres_exporter --config.file=/etc/postgres_exporter.yml'
- name: pgbouncer-exporter
user: postgres
sysvInitAction: respawn
@@ -59,7 +59,7 @@ files:
# the rules use ALL as the hostname. Avoid the pointless lookups and the "unable to
# resolve host" log messages that they generate.
Defaults !fqdn
# Allow postgres user (which is what compute_ctl runs as) to run /neonvm/bin/resize-swap
# and /neonvm/bin/set-disk-quota as root without requiring entering a password (NOPASSWD),
# regardless of hostname (ALL)

View File

@@ -22,11 +22,11 @@ commands:
- name: local_proxy
user: postgres
sysvInitAction: respawn
shell: 'RUST_LOG="error" /usr/local/bin/local_proxy --config-path /etc/local_proxy/config.json --pid-path /etc/local_proxy/pid --http 0.0.0.0:10432'
shell: 'RUST_LOG="info,proxy::serverless::sql_over_http=warn" /usr/local/bin/local_proxy --config-path /etc/local_proxy/config.json --pid-path /etc/local_proxy/pid --http 0.0.0.0:10432'
- name: postgres-exporter
user: nobody
sysvInitAction: respawn
shell: 'DATA_SOURCE_NAME="user=cloud_admin sslmode=disable dbname=postgres application_name=postgres-exporter pgaudit.log=none" /bin/postgres_exporter --config.file=/etc/postgres_exporter.yml'
shell: 'DATA_SOURCE_NAME="user=cloud_admin sslmode=disable dbname=postgres application_name=postgres-exporter" /bin/postgres_exporter --config.file=/etc/postgres_exporter.yml'
- name: pgbouncer-exporter
user: postgres
sysvInitAction: respawn
@@ -59,7 +59,7 @@ files:
# the rules use ALL as the hostname. Avoid the pointless lookups and the "unable to
# resolve host" log messages that they generate.
Defaults !fqdn
# Allow postgres user (which is what compute_ctl runs as) to run /neonvm/bin/resize-swap
# and /neonvm/bin/set-disk-quota as root without requiring entering a password (NOPASSWD),
# regardless of hostname (ALL)

View File

@@ -10,7 +10,6 @@ default = []
testing = ["fail/failpoints"]
[dependencies]
async-compression.workspace = true
base64.workspace = true
aws-config.workspace = true
aws-sdk-s3.workspace = true
@@ -28,7 +27,6 @@ flate2.workspace = true
futures.workspace = true
http.workspace = true
indexmap.workspace = true
itertools.workspace = true
jsonwebtoken.workspace = true
metrics.workspace = true
nix.workspace = true
@@ -64,7 +62,6 @@ uuid.workspace = true
walkdir.workspace = true
x509-cert.workspace = true
postgres_versioninfo.workspace = true
postgres_initdb.workspace = true
compute_api.workspace = true
utils.workspace = true

View File

@@ -40,7 +40,7 @@ use std::sync::mpsc;
use std::thread;
use std::time::Duration;
use anyhow::{Context, Result, bail};
use anyhow::{Context, Result};
use clap::Parser;
use compute_api::responses::ComputeConfig;
use compute_tools::compute::{
@@ -57,15 +57,25 @@ use tracing::{error, info};
use url::Url;
use utils::failpoint_support;
#[derive(Debug, Parser)]
// Compatibility hack: if the control plane specified any remote-ext-config
// use the default value for extension storage proxy gateway.
// Remove this once the control plane is updated to pass the gateway URL
fn parse_remote_ext_config(arg: &str) -> Result<String> {
if arg.starts_with("http") {
Ok(arg.trim_end_matches('/').to_string())
} else {
Ok("http://pg-ext-s3-gateway".to_string())
}
}
#[derive(Parser)]
#[command(rename_all = "kebab-case")]
struct Cli {
#[arg(short = 'b', long, default_value = "postgres", env = "POSTGRES_PATH")]
pub pgbin: String,
/// The base URL for the remote extension storage proxy gateway.
#[arg(short = 'r', long, value_parser = Self::parse_remote_ext_base_url)]
pub remote_ext_base_url: Option<Url>,
#[arg(short = 'r', long, value_parser = parse_remote_ext_config)]
pub remote_ext_config: Option<String>,
/// The port to bind the external listening HTTP server to. Clients running
/// outside the compute will talk to the compute through this port. Keep
@@ -120,33 +130,6 @@ struct Cli {
requires = "compute-id"
)]
pub control_plane_uri: Option<String>,
/// Interval in seconds for collecting installed extensions statistics
#[arg(long, default_value = "3600")]
pub installed_extensions_collection_interval: u64,
/// Run in development mode, skipping VM-specific operations like process termination
#[arg(long, action = clap::ArgAction::SetTrue)]
pub dev: bool,
}
impl Cli {
/// Parse a URL from an argument. By default, this isn't necessary, but we
/// want to do some sanity checking.
fn parse_remote_ext_base_url(value: &str) -> Result<Url> {
// Remove extra trailing slashes, and add one. We use Url::join() later
// when downloading remote extensions. If the base URL is something like
// http://example.com/pg-ext-s3-gateway, and join() is called with
// something like "xyz", the resulting URL is http://example.com/xyz.
let value = value.trim_end_matches('/').to_owned() + "/";
let url = Url::parse(&value)?;
if url.query_pairs().count() != 0 {
bail!("parameters detected in remote extensions base URL")
}
Ok(url)
}
}
fn main() -> Result<()> {
@@ -163,7 +146,7 @@ fn main() -> Result<()> {
.build()?;
let _rt_guard = runtime.enter();
runtime.block_on(init(cli.dev))?;
runtime.block_on(init())?;
// enable core dumping for all child processes
setrlimit(Resource::CORE, rlimit::INFINITY, rlimit::INFINITY)?;
@@ -181,7 +164,7 @@ fn main() -> Result<()> {
pgversion: get_pg_version_string(&cli.pgbin),
external_http_port: cli.external_http_port,
internal_http_port: cli.internal_http_port,
remote_ext_base_url: cli.remote_ext_base_url.clone(),
ext_remote_storage: cli.remote_ext_config.clone(),
resize_swap_on_bind: cli.resize_swap_on_bind,
set_disk_quota_for_fs: cli.set_disk_quota_for_fs,
#[cfg(target_os = "linux")]
@@ -190,7 +173,6 @@ fn main() -> Result<()> {
cgroup: cli.cgroup,
#[cfg(target_os = "linux")]
vm_monitor_addr: cli.vm_monitor_addr,
installed_extensions_collection_interval: cli.installed_extensions_collection_interval,
},
config,
)?;
@@ -202,13 +184,13 @@ fn main() -> Result<()> {
deinit_and_exit(exit_code);
}
async fn init(dev_mode: bool) -> Result<()> {
async fn init() -> Result<()> {
init_tracing_and_logging(DEFAULT_LOG_LEVEL).await?;
let mut signals = Signals::new([SIGINT, SIGTERM, SIGQUIT])?;
thread::spawn(move || {
for sig in signals.forever() {
handle_exit_signal(sig, dev_mode);
handle_exit_signal(sig);
}
});
@@ -267,16 +249,15 @@ fn deinit_and_exit(exit_code: Option<i32>) -> ! {
/// When compute_ctl is killed, send also termination signal to sync-safekeepers
/// to prevent leakage. TODO: it is better to convert compute_ctl to async and
/// wait for termination which would be easy then.
fn handle_exit_signal(sig: i32, dev_mode: bool) {
fn handle_exit_signal(sig: i32) {
info!("received {sig} termination signal");
forward_termination_signal(dev_mode);
forward_termination_signal();
exit(1);
}
#[cfg(test)]
mod test {
use clap::{CommandFactory, Parser};
use url::Url;
use clap::CommandFactory;
use super::Cli;
@@ -284,43 +265,4 @@ mod test {
fn verify_cli() {
Cli::command().debug_assert()
}
#[test]
fn verify_remote_ext_base_url() {
let cli = Cli::parse_from([
"compute_ctl",
"--pgdata=test",
"--connstr=test",
"--compute-id=test",
"--remote-ext-base-url",
"https://example.com/subpath",
]);
assert_eq!(
cli.remote_ext_base_url.unwrap(),
Url::parse("https://example.com/subpath/").unwrap()
);
let cli = Cli::parse_from([
"compute_ctl",
"--pgdata=test",
"--connstr=test",
"--compute-id=test",
"--remote-ext-base-url",
"https://example.com//",
]);
assert_eq!(
cli.remote_ext_base_url.unwrap(),
Url::parse("https://example.com").unwrap()
);
Cli::try_parse_from([
"compute_ctl",
"--pgdata=test",
"--connstr=test",
"--compute-id=test",
"--remote-ext-base-url",
"https://example.com?hello=world",
])
.expect_err("URL parameters are not allowed");
}
}

View File

@@ -29,7 +29,7 @@ use anyhow::{Context, bail};
use aws_config::BehaviorVersion;
use camino::{Utf8Path, Utf8PathBuf};
use clap::{Parser, Subcommand};
use compute_tools::extension_server::get_pg_version;
use compute_tools::extension_server::{PostgresMajorVersion, get_pg_version};
use nix::unistd::Pid;
use std::ops::Not;
use tracing::{Instrument, error, info, info_span, warn};
@@ -179,8 +179,12 @@ impl PostgresProcess {
.await
.context("create pgdata directory")?;
let pg_version = get_pg_version(self.pgbin.as_ref());
let pg_version = match get_pg_version(self.pgbin.as_ref()) {
PostgresMajorVersion::V14 => 14,
PostgresMajorVersion::V15 => 15,
PostgresMajorVersion::V16 => 16,
PostgresMajorVersion::V17 => 17,
};
postgres_initdb::do_run_initdb(postgres_initdb::RunInitdbArgs {
superuser: initdb_user,
locale: DEFAULT_LOCALE, // XXX: this shouldn't be hard-coded,
@@ -335,8 +339,6 @@ async fn run_dump_restore(
destination_connstring: String,
) -> Result<(), anyhow::Error> {
let dumpdir = workdir.join("dumpdir");
let num_jobs = num_cpus::get().to_string();
info!("using {num_jobs} jobs for dump/restore");
let common_args = [
// schema mapping (prob suffices to specify them on one side)
@@ -346,13 +348,12 @@ async fn run_dump_restore(
"--no-security-labels".to_string(),
"--no-subscriptions".to_string(),
"--no-tablespaces".to_string(),
"--no-event-triggers".to_string(),
// format
"--format".to_string(),
"directory".to_string(),
// concurrency
"--jobs".to_string(),
num_jobs,
num_cpus::get().to_string(),
// progress updates
"--verbose".to_string(),
];
@@ -482,8 +483,10 @@ async fn cmd_pgdata(
};
let superuser = "cloud_admin";
let destination_connstring =
format!("host=localhost port={pg_port} user={superuser} dbname=neondb");
let destination_connstring = format!(
"host=localhost port={} user={} dbname=neondb",
pg_port, superuser
);
let pgdata_dir = workdir.join("pgdata");
let mut proc = PostgresProcess::new(pgdata_dir.clone(), pg_bin_dir.clone(), pg_lib_dir.clone());

View File

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

View File

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

View File

@@ -1,26 +1,4 @@
use anyhow::{Context, Result};
use chrono::{DateTime, Utc};
use compute_api::privilege::Privilege;
use compute_api::responses::{
ComputeConfig, ComputeCtlConfig, ComputeMetrics, ComputeStatus, LfcOffloadState,
LfcPrewarmState, TlsConfig,
};
use compute_api::spec::{
ComputeAudit, ComputeFeature, ComputeMode, ComputeSpec, ExtVersion, PgIdent,
};
use futures::StreamExt;
use futures::future::join_all;
use futures::stream::FuturesUnordered;
use itertools::Itertools;
use nix::sys::signal::{Signal, kill};
use nix::unistd::Pid;
use once_cell::sync::Lazy;
use postgres;
use postgres::NoTls;
use postgres::error::SqlState;
use remote_storage::{DownloadError, RemotePath};
use std::collections::{HashMap, HashSet};
use std::net::SocketAddr;
use std::collections::HashMap;
use std::os::unix::fs::{PermissionsExt, symlink};
use std::path::Path;
use std::process::{Command, Stdio};
@@ -29,13 +7,29 @@ use std::sync::atomic::{AtomicU32, Ordering};
use std::sync::{Arc, Condvar, Mutex, RwLock};
use std::time::{Duration, Instant};
use std::{env, fs};
use anyhow::{Context, Result};
use chrono::{DateTime, Utc};
use compute_api::privilege::Privilege;
use compute_api::responses::{ComputeConfig, ComputeCtlConfig, ComputeMetrics, ComputeStatus};
use compute_api::spec::{
ComputeAudit, ComputeFeature, ComputeMode, ComputeSpec, ExtVersion, PgIdent,
};
use futures::StreamExt;
use futures::future::join_all;
use futures::stream::FuturesUnordered;
use nix::sys::signal::{Signal, kill};
use nix::unistd::Pid;
use once_cell::sync::Lazy;
use postgres;
use postgres::NoTls;
use postgres::error::SqlState;
use remote_storage::{DownloadError, RemotePath};
use tokio::spawn;
use tracing::{Instrument, debug, error, info, instrument, warn};
use url::Url;
use utils::id::{TenantId, TimelineId};
use utils::lsn::Lsn;
use utils::measured_stream::MeasuredReader;
use utils::pid_file;
use crate::configurator::launch_configurator;
use crate::disk_quota::set_disk_quota;
@@ -45,7 +39,6 @@ use crate::lsn_lease::launch_lsn_lease_bg_task_for_static;
use crate::metrics::COMPUTE_CTL_UP;
use crate::monitor::launch_monitor;
use crate::pg_helpers::*;
use crate::pgbouncer::*;
use crate::rsyslog::{
PostgresLogsRsyslogConfig, configure_audit_rsyslog, configure_postgres_logs_export,
launch_pgaudit_gc,
@@ -99,10 +92,7 @@ pub struct ComputeNodeParams {
pub internal_http_port: u16,
/// the address of extension storage proxy gateway
pub remote_ext_base_url: Option<Url>,
/// Interval for installed extensions collection
pub installed_extensions_collection_interval: u64,
pub ext_remote_storage: Option<String>,
}
/// Compute node info shared across several `compute_ctl` threads.
@@ -160,13 +150,6 @@ pub struct ComputeState {
/// set up the span relationship ourselves.
pub startup_span: Option<tracing::span::Span>,
pub lfc_prewarm_state: LfcPrewarmState,
pub lfc_offload_state: LfcOffloadState,
/// WAL flush LSN that is set after terminating Postgres and syncing safekeepers if
/// mode == ComputeMode::Primary. None otherwise
pub terminate_flush_lsn: Option<Lsn>,
pub metrics: ComputeMetrics,
}
@@ -180,9 +163,6 @@ impl ComputeState {
pspec: None,
startup_span: None,
metrics: ComputeMetrics::default(),
lfc_prewarm_state: LfcPrewarmState::default(),
lfc_offload_state: LfcOffloadState::default(),
terminate_flush_lsn: None,
}
}
@@ -218,47 +198,6 @@ pub struct ParsedSpec {
pub pageserver_connstr: String,
pub safekeeper_connstrings: Vec<String>,
pub storage_auth_token: Option<String>,
pub endpoint_storage_addr: Option<SocketAddr>,
pub endpoint_storage_token: Option<String>,
}
impl ParsedSpec {
pub fn validate(&self) -> Result<(), String> {
// Only Primary nodes are using safekeeper_connstrings, and at the moment
// this method only validates that part of the specs.
if self.spec.mode != ComputeMode::Primary {
return Ok(());
}
// While it seems like a good idea to check for an odd number of entries in
// the safekeepers connection string, changes to the list of safekeepers might
// incur appending a new server to a list of 3, in which case a list of 4
// entries is okay in production.
//
// Still we want unique entries, and at least one entry in the vector
if self.safekeeper_connstrings.is_empty() {
return Err(String::from("safekeeper_connstrings is empty"));
}
// check for uniqueness of the connection strings in the set
let mut connstrings = self.safekeeper_connstrings.clone();
connstrings.sort();
let mut previous = &connstrings[0];
for current in connstrings.iter().skip(1) {
// duplicate entry?
if current == previous {
return Err(format!(
"duplicate entry in safekeeper_connstrings: {current}!",
));
}
previous = current;
}
Ok(())
}
}
impl TryFrom<ComputeSpec> for ParsedSpec {
@@ -290,7 +229,6 @@ impl TryFrom<ComputeSpec> for ParsedSpec {
} else {
spec.safekeeper_connstrings.clone()
};
let storage_auth_token = spec.storage_auth_token.clone();
let tenant_id: TenantId = if let Some(tenant_id) = spec.tenant_id {
tenant_id
@@ -313,32 +251,14 @@ impl TryFrom<ComputeSpec> for ParsedSpec {
.or(Err("invalid timeline id"))?
};
let endpoint_storage_addr: Option<SocketAddr> = spec
.endpoint_storage_addr
.clone()
.or_else(|| spec.cluster.settings.find("neon.endpoint_storage_addr"))
.unwrap_or_default()
.parse()
.ok();
let endpoint_storage_token = spec
.endpoint_storage_token
.clone()
.or_else(|| spec.cluster.settings.find("neon.endpoint_storage_token"));
let res = ParsedSpec {
Ok(ParsedSpec {
spec,
pageserver_connstr,
safekeeper_connstrings,
storage_auth_token,
tenant_id,
timeline_id,
endpoint_storage_addr,
endpoint_storage_token,
};
// Now check validity of the parsed specification
res.validate()?;
Ok(res)
})
}
}
@@ -385,36 +305,11 @@ struct StartVmMonitorResult {
impl ComputeNode {
pub fn new(params: ComputeNodeParams, config: ComputeConfig) -> Result<Self> {
let connstr = params.connstr.as_str();
let mut conn_conf = postgres::config::Config::from_str(connstr)
let conn_conf = postgres::config::Config::from_str(connstr)
.context("cannot build postgres config from connstr")?;
let mut tokio_conn_conf = tokio_postgres::config::Config::from_str(connstr)
let tokio_conn_conf = tokio_postgres::config::Config::from_str(connstr)
.context("cannot build tokio postgres config from connstr")?;
// Users can set some configuration parameters per database with
// ALTER DATABASE ... SET ...
//
// There are at least these parameters:
//
// - role=some_other_role
// - default_transaction_read_only=on
// - statement_timeout=1, i.e., 1ms, which will cause most of the queries to fail
// - search_path=non_public_schema, this should be actually safe because
// we don't call any functions in user databases, but better to always reset
// it to public.
//
// that can affect `compute_ctl` and prevent it from properly configuring the database schema.
// Unset them via connection string options before connecting to the database.
// N.B. keep it in sync with `ZENITH_OPTIONS` in `get_maintenance_client()`.
const EXTRA_OPTIONS: &str = "-c role=cloud_admin -c default_transaction_read_only=off -c search_path=public -c statement_timeout=0 -c pgaudit.log=none";
let options = match conn_conf.get_options() {
// Allow the control plane to override any options set by the
// compute
Some(options) => format!("{EXTRA_OPTIONS} {options}"),
None => EXTRA_OPTIONS.to_string(),
};
conn_conf.options(&options);
tokio_conn_conf.options(&options);
let mut new_state = ComputeState::new();
if let Some(spec) = config.spec {
let pspec = ParsedSpec::try_from(spec).map_err(|msg| anyhow::anyhow!(msg))?;
@@ -444,7 +339,7 @@ impl ComputeNode {
// because QEMU will already have its memory allocated from the host, and
// the necessary binaries will already be cached.
if cli_spec.is_none() {
this.prewarm_postgres_vm_memory()?;
this.prewarm_postgres()?;
}
// Set the up metric with Empty status before starting the HTTP server.
@@ -537,21 +432,12 @@ impl ComputeNode {
// Reap the postgres process
delay_exit |= this.cleanup_after_postgres_exit()?;
// /terminate returns LSN. If we don't sleep at all, connection will break and we
// won't get result. If we sleep too much, tests will take significantly longer
// and Github Action run will error out
let sleep_duration = if delay_exit {
Duration::from_secs(30)
} else {
Duration::from_millis(300)
};
// If launch failed, keep serving HTTP requests for a while, so the cloud
// control plane can get the actual error.
if delay_exit {
info!("giving control plane 30s to collect the error before shutdown");
std::thread::sleep(Duration::from_secs(30));
}
std::thread::sleep(sleep_duration);
Ok(exit_code)
}
@@ -660,8 +546,6 @@ impl ComputeNode {
});
}
let tls_config = self.tls_config(&pspec.spec);
// If there are any remote extensions in shared_preload_libraries, start downloading them
if pspec.spec.remote_extensions.is_some() {
let (this, spec) = (self.clone(), pspec.spec.clone());
@@ -718,7 +602,7 @@ impl ComputeNode {
info!("tuning pgbouncer");
let pgbouncer_settings = pgbouncer_settings.clone();
let tls_config = tls_config.clone();
let tls_config = self.compute_ctl_config.tls.clone();
// Spawn a background task to do the tuning,
// so that we don't block the main thread that starts Postgres.
@@ -737,10 +621,7 @@ impl ComputeNode {
// Spawn a background task to do the configuration,
// so that we don't block the main thread that starts Postgres.
let mut local_proxy = local_proxy.clone();
local_proxy.tls = tls_config.clone();
let local_proxy = local_proxy.clone();
let _handle = tokio::spawn(async move {
if let Err(err) = local_proxy::configure(&local_proxy) {
error!("error while configuring local_proxy: {err:?}");
@@ -761,18 +642,25 @@ impl ComputeNode {
let log_directory_path = Path::new(&self.params.pgdata).join("log");
let log_directory_path = log_directory_path.to_string_lossy().to_string();
// Add project_id,endpoint_id to identify the logs.
// Add project_id,endpoint_id tag to identify the logs.
//
// These ids are passed from cplane,
let endpoint_id = pspec.spec.endpoint_id.as_deref().unwrap_or("");
let project_id = pspec.spec.project_id.as_deref().unwrap_or("");
// for backwards compatibility (old computes that don't have them),
// we set them to None.
// TODO: Clean up this code when all computes have them.
let tag: Option<String> = match (
pspec.spec.project_id.as_deref(),
pspec.spec.endpoint_id.as_deref(),
) {
(Some(project_id), Some(endpoint_id)) => {
Some(format!("{project_id}/{endpoint_id}"))
}
(Some(project_id), None) => Some(format!("{project_id}/None")),
(None, Some(endpoint_id)) => Some(format!("None,{endpoint_id}")),
(None, None) => None,
};
configure_audit_rsyslog(
log_directory_path.clone(),
endpoint_id,
project_id,
&remote_endpoint,
)?;
configure_audit_rsyslog(log_directory_path.clone(), tag, &remote_endpoint)?;
// Launch a background task to clean up the audit logs
launch_pgaudit_gc(log_directory_path);
@@ -808,7 +696,17 @@ impl ComputeNode {
let conf = self.get_tokio_conn_conf(None);
tokio::task::spawn(async {
let _ = installed_extensions(conf).await;
let res = get_installed_extensions(conf).await;
match res {
Ok(extensions) => {
info!(
"[NEON_EXT_STAT] {}",
serde_json::to_string(&extensions)
.expect("failed to serialize extensions list")
);
}
Err(err) => error!("could not get installed extensions: {err:?}"),
}
});
}
@@ -838,12 +736,6 @@ impl ComputeNode {
// Log metrics so that we can search for slow operations in logs
info!(?metrics, postmaster_pid = %postmaster_pid, "compute start finished");
// Spawn the extension stats background task
self.spawn_extension_stats_task();
if pspec.spec.autoprewarm {
self.prewarm_lfc(None);
}
Ok(())
}
@@ -923,25 +815,20 @@ impl ComputeNode {
// Maybe sync safekeepers again, to speed up next startup
let compute_state = self.state.lock().unwrap().clone();
let pspec = compute_state.pspec.as_ref().expect("spec must be set");
let lsn = if matches!(pspec.spec.mode, compute_api::spec::ComputeMode::Primary) {
if matches!(pspec.spec.mode, compute_api::spec::ComputeMode::Primary) {
info!("syncing safekeepers on shutdown");
let storage_auth_token = pspec.storage_auth_token.clone();
let lsn = self.sync_safekeepers(storage_auth_token)?;
info!(%lsn, "synced safekeepers");
Some(lsn)
} else {
info!("not primary, not syncing safekeepers");
None
};
info!("synced safekeepers at lsn {lsn}");
}
let mut delay_exit = false;
let mut state = self.state.lock().unwrap();
state.terminate_flush_lsn = lsn;
if let ComputeStatus::TerminationPending { mode } = state.status {
if state.status == ComputeStatus::TerminationPending {
state.status = ComputeStatus::Terminated;
self.state_changed.notify_all();
// we were asked to terminate gracefully, don't exit to avoid restart
delay_exit = mode == compute_api::responses::TerminateMode::Fast
delay_exit = true
}
drop(state);
@@ -1126,7 +1013,7 @@ impl ComputeNode {
let sk_configs = sk_connstrs.into_iter().map(|connstr| {
// Format connstr
let id = connstr.clone();
let connstr = format!("postgresql://no_user@{connstr}");
let connstr = format!("postgresql://no_user@{}", connstr);
let options = format!(
"-c timeline_id={} tenant_id={}",
pspec.timeline_id, pspec.tenant_id
@@ -1272,15 +1159,13 @@ impl ComputeNode {
let spec = &pspec.spec;
let pgdata_path = Path::new(&self.params.pgdata);
let tls_config = self.tls_config(&pspec.spec);
// Remove/create an empty pgdata directory and put configuration there.
self.create_pgdata()?;
config::write_postgres_conf(
pgdata_path,
&pspec.spec,
self.params.internal_http_port,
tls_config,
&self.compute_ctl_config.tls,
)?;
// Syncing safekeepers is only safe with primary nodes: if a primary
@@ -1376,8 +1261,8 @@ impl ComputeNode {
}
/// Start and stop a postgres process to warm up the VM for startup.
pub fn prewarm_postgres_vm_memory(&self) -> Result<()> {
info!("prewarming VM memory");
pub fn prewarm_postgres(&self) -> Result<()> {
info!("prewarming");
// Create pgdata
let pgdata = &format!("{}.warmup", self.params.pgdata);
@@ -1419,7 +1304,7 @@ impl ComputeNode {
kill(pm_pid, Signal::SIGQUIT)?;
info!("sent SIGQUIT signal");
pg.wait()?;
info!("done prewarming vm memory");
info!("done prewarming");
// clean up
let _ok = fs::remove_dir_all(pgdata);
@@ -1489,7 +1374,7 @@ impl ComputeNode {
let (mut client, connection) = conf.connect(NoTls).await?;
tokio::spawn(async move {
if let Err(e) = connection.await {
eprintln!("connection error: {e}");
eprintln!("connection error: {}", e);
}
});
@@ -1537,20 +1422,15 @@ impl ComputeNode {
Err(e) => match e.code() {
Some(&SqlState::INVALID_PASSWORD)
| Some(&SqlState::INVALID_AUTHORIZATION_SPECIFICATION) => {
// Connect with `zenith_admin` if `cloud_admin` could not authenticate
// Connect with zenith_admin if cloud_admin could not authenticate
info!(
"cannot connect to Postgres: {}, retrying with 'zenith_admin' username",
"cannot connect to postgres: {}, retrying with `zenith_admin` username",
e
);
let mut zenith_admin_conf = postgres::config::Config::from(conf.clone());
zenith_admin_conf.application_name("compute_ctl:apply_config");
zenith_admin_conf.user("zenith_admin");
// It doesn't matter what were the options before, here we just want
// to connect and create a new superuser role.
const ZENITH_OPTIONS: &str = "-c role=zenith_admin -c default_transaction_read_only=off -c search_path=public -c statement_timeout=0";
zenith_admin_conf.options(ZENITH_OPTIONS);
let mut client =
zenith_admin_conf.connect(NoTls)
.context("broken cloud_admin credential: tried connecting with cloud_admin but could not authenticate, and zenith_admin does not work either")?;
@@ -1605,22 +1485,14 @@ impl ComputeNode {
.clone(),
);
let mut tls_config = None::<TlsConfig>;
if spec.features.contains(&ComputeFeature::TlsExperimental) {
tls_config = self.compute_ctl_config.tls.clone();
}
let max_concurrent_connections = self.max_service_connections(compute_state, &spec);
// Merge-apply spec & changes to PostgreSQL state.
self.apply_spec_sql(spec.clone(), conf.clone(), max_concurrent_connections)?;
if let Some(local_proxy) = &spec.clone().local_proxy_config {
let mut local_proxy = local_proxy.clone();
local_proxy.tls = tls_config.clone();
info!("configuring local_proxy");
local_proxy::configure(&local_proxy).context("apply_config local_proxy")?;
local_proxy::configure(local_proxy).context("apply_config local_proxy")?;
}
// Run migrations separately to not hold up cold starts
@@ -1632,7 +1504,7 @@ impl ComputeNode {
Ok((mut client, connection)) => {
tokio::spawn(async move {
if let Err(e) = connection.await {
eprintln!("connection error: {e}");
eprintln!("connection error: {}", e);
}
});
if let Err(e) = handle_migrations(&mut client).await {
@@ -1672,13 +1544,11 @@ impl ComputeNode {
pub fn reconfigure(&self) -> Result<()> {
let spec = self.state.lock().unwrap().pspec.clone().unwrap().spec;
let tls_config = self.tls_config(&spec);
if let Some(ref pgbouncer_settings) = spec.pgbouncer_settings {
info!("tuning pgbouncer");
let pgbouncer_settings = pgbouncer_settings.clone();
let tls_config = tls_config.clone();
let tls_config = self.compute_ctl_config.tls.clone();
// Spawn a background task to do the tuning,
// so that we don't block the main thread that starts Postgres.
@@ -1696,7 +1566,7 @@ impl ComputeNode {
// Spawn a background task to do the configuration,
// so that we don't block the main thread that starts Postgres.
let mut local_proxy = local_proxy.clone();
local_proxy.tls = tls_config.clone();
local_proxy.tls = self.compute_ctl_config.tls.clone();
tokio::spawn(async move {
if let Err(err) = local_proxy::configure(&local_proxy) {
error!("error while configuring local_proxy: {err:?}");
@@ -1714,7 +1584,7 @@ impl ComputeNode {
pgdata_path,
&spec,
self.params.internal_http_port,
tls_config,
&self.compute_ctl_config.tls,
)?;
if !spec.skip_pg_catalog_updates {
@@ -1726,7 +1596,9 @@ impl ComputeNode {
self.pg_reload_conf()?;
if spec.mode == ComputeMode::Primary {
let conf = self.get_tokio_conn_conf(Some("compute_ctl:reconfigure"));
let mut conf =
tokio_postgres::Config::from_str(self.params.connstr.as_str()).unwrap();
conf.application_name("apply_config");
let conf = Arc::new(conf);
let spec = Arc::new(spec.clone());
@@ -1812,7 +1684,7 @@ impl ComputeNode {
// exit loop
ComputeStatus::Failed
| ComputeStatus::TerminationPending { .. }
| ComputeStatus::TerminationPending
| ComputeStatus::Terminated => break 'cert_update,
// wait
@@ -1834,14 +1706,6 @@ impl ComputeNode {
}
}
pub fn tls_config(&self, spec: &ComputeSpec) -> &Option<TlsConfig> {
if spec.features.contains(&ComputeFeature::TlsExperimental) {
&self.compute_ctl_config.tls
} else {
&None::<TlsConfig>
}
}
/// Update the `last_active` in the shared state, but ensure that it's a more recent one.
pub fn update_last_active(&self, last_active: Option<DateTime<Utc>>) {
let mut state = self.state.lock().unwrap();
@@ -1936,7 +1800,7 @@ impl ComputeNode {
let (client, connection) = connect_result.unwrap();
tokio::spawn(async move {
if let Err(e) = connection.await {
eprintln!("connection error: {e}");
eprintln!("connection error: {}", e);
}
});
let result = client
@@ -1974,9 +1838,9 @@ LIMIT 100",
real_ext_name: String,
ext_path: RemotePath,
) -> Result<u64, DownloadError> {
let remote_ext_base_url =
let ext_remote_storage =
self.params
.remote_ext_base_url
.ext_remote_storage
.as_ref()
.ok_or(DownloadError::BadInput(anyhow::anyhow!(
"Remote extensions storage is not configured",
@@ -2038,7 +1902,7 @@ LIMIT 100",
let download_size = extension_server::download_extension(
&real_ext_name,
&ext_path,
remote_ext_base_url,
ext_remote_storage,
&self.params.pgbin,
)
.await
@@ -2073,40 +1937,23 @@ LIMIT 100",
tokio::spawn(conn);
// TODO: support other types of grants apart from schemas?
// check the role grants first - to gracefully handle read-replicas.
let select = "SELECT privilege_type
FROM pg_namespace
JOIN LATERAL (SELECT * FROM aclexplode(nspacl) AS x) acl ON true
JOIN pg_user users ON acl.grantee = users.usesysid
WHERE users.usename = $1
AND nspname = $2";
let rows = db_client
.query(select, &[role_name, schema_name])
.await
.with_context(|| format!("Failed to execute query: {select}"))?;
let already_granted: HashSet<String> = rows.into_iter().map(|row| row.get(0)).collect();
let grants = privileges
.iter()
.filter(|p| !already_granted.contains(p.as_str()))
// should not be quoted as it's part of the command.
// is already sanitized so it's ok
.map(|p| p.as_str())
.join(", ");
if !grants.is_empty() {
let query = format!(
"GRANT {} ON SCHEMA {} TO {}",
privileges
.iter()
// should not be quoted as it's part of the command.
// is already sanitized so it's ok
.map(|p| p.as_str())
.collect::<Vec<&'static str>>()
.join(", "),
// quote the schema and role name as identifiers to sanitize them.
let schema_name = schema_name.pg_quote();
let role_name = role_name.pg_quote();
let query = format!("GRANT {grants} ON SCHEMA {schema_name} TO {role_name}",);
db_client
.simple_query(&query)
.await
.with_context(|| format!("Failed to execute query: {query}"))?;
}
schema_name.pg_quote(),
role_name.pg_quote(),
);
db_client
.simple_query(&query)
.await
.with_context(|| format!("Failed to execute query: {}", query))?;
Ok(())
}
@@ -2132,7 +1979,7 @@ LIMIT 100",
let version: Option<ExtVersion> = db_client
.query_opt(version_query, &[&ext_name])
.await
.with_context(|| format!("Failed to execute query: {version_query}"))?
.with_context(|| format!("Failed to execute query: {}", version_query))?
.map(|row| row.get(0));
// sanitize the inputs as postgres idents.
@@ -2147,14 +1994,14 @@ LIMIT 100",
db_client
.simple_query(&query)
.await
.with_context(|| format!("Failed to execute query: {query}"))?;
.with_context(|| format!("Failed to execute query: {}", query))?;
} else {
let query =
format!("CREATE EXTENSION IF NOT EXISTS {ext_name} WITH VERSION {quoted_version}");
db_client
.simple_query(&query)
.await
.with_context(|| format!("Failed to execute query: {query}"))?;
.with_context(|| format!("Failed to execute query: {}", query))?;
}
Ok(ext_version)
@@ -2164,7 +2011,7 @@ LIMIT 100",
&self,
spec: &ComputeSpec,
) -> Result<RemoteExtensionMetrics> {
if self.params.remote_ext_base_url.is_none() {
if self.params.ext_remote_storage.is_none() {
return Ok(RemoteExtensionMetrics {
num_ext_downloaded: 0,
largest_ext_size: 0,
@@ -2276,105 +2123,14 @@ LIMIT 100",
info!("Pageserver config changed");
}
}
pub fn spawn_extension_stats_task(&self) {
let conf = self.tokio_conn_conf.clone();
let installed_extensions_collection_interval =
self.params.installed_extensions_collection_interval;
tokio::spawn(async move {
// An initial sleep is added to ensure that two collections don't happen at the same time.
// The first collection happens during compute startup.
tokio::time::sleep(tokio::time::Duration::from_secs(
installed_extensions_collection_interval,
))
.await;
let mut interval = tokio::time::interval(tokio::time::Duration::from_secs(
installed_extensions_collection_interval,
));
loop {
interval.tick().await;
let _ = installed_extensions(conf.clone()).await;
}
});
}
}
pub async fn installed_extensions(conf: tokio_postgres::Config) -> Result<()> {
let res = get_installed_extensions(conf).await;
match res {
Ok(extensions) => {
info!(
"[NEON_EXT_STAT] {}",
serde_json::to_string(&extensions).expect("failed to serialize extensions list")
);
}
Err(err) => error!("could not get installed extensions: {err:?}"),
}
Ok(())
}
pub fn forward_termination_signal(dev_mode: bool) {
pub fn forward_termination_signal() {
let ss_pid = SYNC_SAFEKEEPERS_PID.load(Ordering::SeqCst);
if ss_pid != 0 {
let ss_pid = nix::unistd::Pid::from_raw(ss_pid as i32);
kill(ss_pid, Signal::SIGTERM).ok();
}
if !dev_mode {
// Terminate pgbouncer with SIGKILL
match pid_file::read(PGBOUNCER_PIDFILE.into()) {
Ok(pid_file::PidFileRead::LockedByOtherProcess(pid)) => {
info!("sending SIGKILL to pgbouncer process pid: {}", pid);
if let Err(e) = kill(pid, Signal::SIGKILL) {
error!("failed to terminate pgbouncer: {}", e);
}
}
// pgbouncer does not lock the pid file, so we read and kill the process directly
Ok(pid_file::PidFileRead::NotHeldByAnyProcess(_)) => {
if let Ok(pid_str) = std::fs::read_to_string(PGBOUNCER_PIDFILE) {
if let Ok(pid) = pid_str.trim().parse::<i32>() {
info!(
"sending SIGKILL to pgbouncer process pid: {} (from unlocked pid file)",
pid
);
if let Err(e) = kill(Pid::from_raw(pid), Signal::SIGKILL) {
error!("failed to terminate pgbouncer: {}", e);
}
}
} else {
info!("pgbouncer pid file exists but process not running");
}
}
Ok(pid_file::PidFileRead::NotExist) => {
info!("pgbouncer pid file not found, process may not be running");
}
Err(e) => {
error!("error reading pgbouncer pid file: {}", e);
}
}
// Terminate local_proxy
match pid_file::read("/etc/local_proxy/pid".into()) {
Ok(pid_file::PidFileRead::LockedByOtherProcess(pid)) => {
info!("sending SIGTERM to local_proxy process pid: {}", pid);
if let Err(e) = kill(pid, Signal::SIGTERM) {
error!("failed to terminate local_proxy: {}", e);
}
}
Ok(pid_file::PidFileRead::NotHeldByAnyProcess(_)) => {
info!("local_proxy PID file exists but process not running");
}
Ok(pid_file::PidFileRead::NotExist) => {
info!("local_proxy PID file not found, process may not be running");
}
Err(e) => {
error!("error reading local_proxy PID file: {}", e);
}
}
} else {
info!("Skipping pgbouncer and local_proxy termination because in dev mode");
}
let pg_pid = PG_PID.load(Ordering::SeqCst);
if pg_pid != 0 {
let pg_pid = nix::unistd::Pid::from_raw(pg_pid as i32);
@@ -2407,21 +2163,3 @@ impl<T: 'static> JoinSetExt<T> for tokio::task::JoinSet<T> {
})
}
}
#[cfg(test)]
mod tests {
use std::fs::File;
use super::*;
#[test]
fn duplicate_safekeeper_connstring() {
let file = File::open("tests/cluster_spec.json").unwrap();
let spec: ComputeSpec = serde_json::from_reader(file).unwrap();
match ParsedSpec::try_from(spec.clone()) {
Ok(_p) => panic!("Failed to detect duplicate entry"),
Err(e) => assert!(e.starts_with("duplicate entry in safekeeper_connstrings:")),
};
}
}

View File

@@ -1,208 +0,0 @@
use crate::compute::ComputeNode;
use anyhow::{Context, Result, bail};
use async_compression::tokio::bufread::{ZstdDecoder, ZstdEncoder};
use compute_api::responses::LfcOffloadState;
use compute_api::responses::LfcPrewarmState;
use http::StatusCode;
use reqwest::Client;
use std::sync::Arc;
use tokio::{io::AsyncReadExt, spawn};
use tracing::{error, info};
#[derive(serde::Serialize, Default)]
pub struct LfcPrewarmStateWithProgress {
#[serde(flatten)]
base: LfcPrewarmState,
total: i32,
prewarmed: i32,
skipped: i32,
}
/// A pair of url and a token to query endpoint storage for LFC prewarm-related tasks
struct EndpointStoragePair {
url: String,
token: String,
}
const KEY: &str = "lfc_state";
impl EndpointStoragePair {
/// endpoint_id is set to None while prewarming from other endpoint, see replica promotion
/// If not None, takes precedence over pspec.spec.endpoint_id
fn from_spec_and_endpoint(
pspec: &crate::compute::ParsedSpec,
endpoint_id: Option<String>,
) -> Result<Self> {
let endpoint_id = endpoint_id.as_ref().or(pspec.spec.endpoint_id.as_ref());
let Some(ref endpoint_id) = endpoint_id else {
bail!("pspec.endpoint_id missing, other endpoint_id not provided")
};
let Some(ref base_uri) = pspec.endpoint_storage_addr else {
bail!("pspec.endpoint_storage_addr missing")
};
let tenant_id = pspec.tenant_id;
let timeline_id = pspec.timeline_id;
let url = format!("http://{base_uri}/{tenant_id}/{timeline_id}/{endpoint_id}/{KEY}");
let Some(ref token) = pspec.endpoint_storage_token else {
bail!("pspec.endpoint_storage_token missing")
};
let token = token.clone();
Ok(EndpointStoragePair { url, token })
}
}
impl ComputeNode {
// If prewarm failed, we want to get overall number of segments as well as done ones.
// However, this function should be reliable even if querying postgres failed.
pub async fn lfc_prewarm_state(&self) -> LfcPrewarmStateWithProgress {
info!("requesting LFC prewarm state from postgres");
let mut state = LfcPrewarmStateWithProgress::default();
{
state.base = self.state.lock().unwrap().lfc_prewarm_state.clone();
}
let client = match ComputeNode::get_maintenance_client(&self.tokio_conn_conf).await {
Ok(client) => client,
Err(err) => {
error!(%err, "connecting to postgres");
return state;
}
};
let row = match client
.query_one("select * from get_prewarm_info()", &[])
.await
{
Ok(row) => row,
Err(err) => {
error!(%err, "querying LFC prewarm status");
return state;
}
};
state.total = row.try_get(0).unwrap_or_default();
state.prewarmed = row.try_get(1).unwrap_or_default();
state.skipped = row.try_get(2).unwrap_or_default();
state
}
pub fn lfc_offload_state(&self) -> LfcOffloadState {
self.state.lock().unwrap().lfc_offload_state.clone()
}
/// Returns false if there is a prewarm request ongoing, true otherwise
pub fn prewarm_lfc(self: &Arc<Self>, from_endpoint: Option<String>) -> bool {
crate::metrics::LFC_PREWARM_REQUESTS.inc();
{
let state = &mut self.state.lock().unwrap().lfc_prewarm_state;
if let LfcPrewarmState::Prewarming =
std::mem::replace(state, LfcPrewarmState::Prewarming)
{
return false;
}
}
let cloned = self.clone();
spawn(async move {
let Err(err) = cloned.prewarm_impl(from_endpoint).await else {
cloned.state.lock().unwrap().lfc_prewarm_state = LfcPrewarmState::Completed;
return;
};
error!(%err);
cloned.state.lock().unwrap().lfc_prewarm_state = LfcPrewarmState::Failed {
error: err.to_string(),
};
});
true
}
/// from_endpoint: None for endpoint managed by this compute_ctl
fn endpoint_storage_pair(&self, from_endpoint: Option<String>) -> Result<EndpointStoragePair> {
let state = self.state.lock().unwrap();
EndpointStoragePair::from_spec_and_endpoint(state.pspec.as_ref().unwrap(), from_endpoint)
}
async fn prewarm_impl(&self, from_endpoint: Option<String>) -> Result<()> {
let EndpointStoragePair { url, token } = self.endpoint_storage_pair(from_endpoint)?;
info!(%url, "requesting LFC state from endpoint storage");
let request = Client::new().get(&url).bearer_auth(token);
let res = request.send().await.context("querying endpoint storage")?;
let status = res.status();
if status != StatusCode::OK {
bail!("{status} querying endpoint storage")
}
let mut uncompressed = Vec::new();
let lfc_state = res
.bytes()
.await
.context("getting request body from endpoint storage")?;
ZstdDecoder::new(lfc_state.iter().as_slice())
.read_to_end(&mut uncompressed)
.await
.context("decoding LFC state")?;
let uncompressed_len = uncompressed.len();
info!(%url, "downloaded LFC state, uncompressed size {uncompressed_len}, loading into postgres");
ComputeNode::get_maintenance_client(&self.tokio_conn_conf)
.await
.context("connecting to postgres")?
.query_one("select prewarm_local_cache($1)", &[&uncompressed])
.await
.context("loading LFC state into postgres")
.map(|_| ())
}
/// Returns false if there is an offload request ongoing, true otherwise
pub fn offload_lfc(self: &Arc<Self>) -> bool {
crate::metrics::LFC_OFFLOAD_REQUESTS.inc();
{
let state = &mut self.state.lock().unwrap().lfc_offload_state;
if let LfcOffloadState::Offloading =
std::mem::replace(state, LfcOffloadState::Offloading)
{
return false;
}
}
let cloned = self.clone();
spawn(async move {
let Err(err) = cloned.offload_lfc_impl().await else {
cloned.state.lock().unwrap().lfc_offload_state = LfcOffloadState::Completed;
return;
};
error!(%err);
cloned.state.lock().unwrap().lfc_offload_state = LfcOffloadState::Failed {
error: err.to_string(),
};
});
true
}
async fn offload_lfc_impl(&self) -> Result<()> {
let EndpointStoragePair { url, token } = self.endpoint_storage_pair(None)?;
info!(%url, "requesting LFC state from postgres");
let mut compressed = Vec::new();
ComputeNode::get_maintenance_client(&self.tokio_conn_conf)
.await
.context("connecting to postgres")?
.query_one("select get_local_cache_state()", &[])
.await
.context("querying LFC state")?
.try_get::<usize, &[u8]>(0)
.context("deserializing LFC state")
.map(ZstdEncoder::new)?
.read_to_end(&mut compressed)
.await
.context("compressing LFC state")?;
let compressed_len = compressed.len();
info!(%url, "downloaded LFC state, compressed size {compressed_len}, writing to endpoint storage");
let request = Client::new().put(url).bearer_auth(token).body(compressed);
match request.send().await {
Ok(res) if res.status() == StatusCode::OK => Ok(()),
Ok(res) => bail!("Error writing to endpoint storage: {}", res.status()),
Err(err) => Err(err).context("writing to endpoint storage"),
}
}
}

View File

@@ -51,7 +51,7 @@ pub fn write_postgres_conf(
// Write the postgresql.conf content from the spec file as is.
if let Some(conf) = &spec.cluster.postgresql_conf {
writeln!(file, "{conf}")?;
writeln!(file, "{}", conf)?;
}
// Add options for connecting to storage
@@ -70,7 +70,7 @@ pub fn write_postgres_conf(
);
// If generation is given, prepend sk list with g#number:
if let Some(generation) = spec.safekeepers_generation {
write!(neon_safekeepers_value, "g#{generation}:")?;
write!(neon_safekeepers_value, "g#{}:", generation)?;
}
neon_safekeepers_value.push_str(&spec.safekeeper_connstrings.join(","));
writeln!(
@@ -109,8 +109,8 @@ pub fn write_postgres_conf(
tls::update_key_path_blocking(pgdata_path, tls_config);
// these are the default, but good to be explicit.
writeln!(file, "ssl_cert_file = '{SERVER_CRT}'")?;
writeln!(file, "ssl_key_file = '{SERVER_KEY}'")?;
writeln!(file, "ssl_cert_file = '{}'", SERVER_CRT)?;
writeln!(file, "ssl_key_file = '{}'", SERVER_KEY)?;
}
// Locales
@@ -191,7 +191,8 @@ pub fn write_postgres_conf(
}
writeln!(
file,
"shared_preload_libraries='{libs}{extra_shared_preload_libraries}'"
"shared_preload_libraries='{}{}'",
libs, extra_shared_preload_libraries
)?;
} else {
// Typically, this should be unreacheable,
@@ -222,12 +223,6 @@ pub fn write_postgres_conf(
// TODO: tune this after performance testing
writeln!(file, "pgaudit.log_rotation_age=5")?;
// Enable audit logs for pg_session_jwt extension
// TODO: Consider a good approach for shipping pg_session_jwt logs to the same sink as
// pgAudit - additional context in https://github.com/neondatabase/cloud/issues/28863
//
// writeln!(file, "pg_session_jwt.audit_log=on")?;
// Add audit shared_preload_libraries, if they are not present.
//
// The caller who sets the flag is responsible for ensuring that the necessary
@@ -243,7 +238,8 @@ pub fn write_postgres_conf(
}
writeln!(
file,
"shared_preload_libraries='{libs}{extra_shared_preload_libraries}'"
"shared_preload_libraries='{}{}'",
libs, extra_shared_preload_libraries
)?;
} else {
// Typically, this should be unreacheable,
@@ -261,7 +257,7 @@ pub fn write_postgres_conf(
}
}
writeln!(file, "neon.extension_server_port={extension_server_port}")?;
writeln!(file, "neon.extension_server_port={}", extension_server_port)?;
if spec.drop_subscriptions_before_start {
writeln!(file, "neon.disable_logical_replication_subscribers=true")?;
@@ -289,7 +285,7 @@ where
{
let path = pgdata_path.join("compute_ctl_temp_override.conf");
let mut file = File::create(path)?;
write!(file, "{options}")?;
write!(file, "{}", options)?;
let res = exec();

View File

@@ -2,24 +2,10 @@
module(load="imfile")
# Input configuration for log files in the specified directory
# The messages can be multiline. The start of the message is a timestamp
# in "%Y-%m-%d %H:%M:%S.%3N GMT" (so timezone hardcoded).
# Replace log_directory with the directory containing the log files
input(type="imfile" File="{log_directory}/*.log"
Tag="pgaudit_log" Severity="info" Facility="local5"
startmsg.regex="^[[:digit:]]{{4}}-[[:digit:]]{{2}}-[[:digit:]]{{2}} [[:digit:]]{{2}}:[[:digit:]]{{2}}:[[:digit:]]{{2}}.[[:digit:]]{{3}} GMT,")
# Replace {log_directory} with the directory containing the log files
input(type="imfile" File="{log_directory}/*.log" Tag="{tag}" Severity="info" Facility="local0")
# the directory to store rsyslog state files
global(workDirectory="/var/log/rsyslog")
# Construct json, endpoint_id and project_id as additional metadata
set $.json_log!endpoint_id = "{endpoint_id}";
set $.json_log!project_id = "{project_id}";
set $.json_log!msg = $msg;
# Template suitable for rfc5424 syslog format
template(name="PgAuditLog" type="string"
string="<%PRI%>1 %TIMESTAMP:::date-rfc3339% %HOSTNAME% - - - - %$.json_log%")
# Forward to remote syslog receiver (@@<hostname>:<port>;format
local5.info @@{remote_endpoint};PgAuditLog
# Forward logs to remote syslog server
*.* @@{remote_endpoint}

View File

@@ -74,20 +74,19 @@ More specifically, here is an example ext_index.json
use std::path::Path;
use std::str;
use crate::metrics::{REMOTE_EXT_REQUESTS_TOTAL, UNKNOWN_HTTP_STATUS};
use anyhow::{Context, Result, bail};
use bytes::Bytes;
use compute_api::spec::RemoteExtSpec;
use postgres_versioninfo::PgMajorVersion;
use regex::Regex;
use remote_storage::*;
use reqwest::StatusCode;
use tar::Archive;
use tracing::info;
use tracing::log::warn;
use url::Url;
use zstd::stream::read::Decoder;
use crate::metrics::{REMOTE_EXT_REQUESTS_TOTAL, UNKNOWN_HTTP_STATUS};
fn get_pg_config(argument: &str, pgbin: &str) -> String {
// gives the result of `pg_config [argument]`
// where argument is a flag like `--version` or `--sharedir`
@@ -106,7 +105,7 @@ fn get_pg_config(argument: &str, pgbin: &str) -> String {
.to_string()
}
pub fn get_pg_version(pgbin: &str) -> PgMajorVersion {
pub fn get_pg_version(pgbin: &str) -> PostgresMajorVersion {
// pg_config --version returns a (platform specific) human readable string
// such as "PostgreSQL 15.4". We parse this to v14/v15/v16 etc.
let human_version = get_pg_config("--version", pgbin);
@@ -114,11 +113,25 @@ pub fn get_pg_version(pgbin: &str) -> PgMajorVersion {
}
pub fn get_pg_version_string(pgbin: &str) -> String {
get_pg_version(pgbin).v_str()
match get_pg_version(pgbin) {
PostgresMajorVersion::V14 => "v14",
PostgresMajorVersion::V15 => "v15",
PostgresMajorVersion::V16 => "v16",
PostgresMajorVersion::V17 => "v17",
}
.to_owned()
}
fn parse_pg_version(human_version: &str) -> PgMajorVersion {
use PgMajorVersion::*;
#[derive(Copy, Clone, Debug, PartialEq, Eq)]
pub enum PostgresMajorVersion {
V14,
V15,
V16,
V17,
}
fn parse_pg_version(human_version: &str) -> PostgresMajorVersion {
use PostgresMajorVersion::*;
// Normal releases have version strings like "PostgreSQL 15.4". But there
// are also pre-release versions like "PostgreSQL 17devel" or "PostgreSQL
// 16beta2" or "PostgreSQL 17rc1". And with the --with-extra-version
@@ -129,10 +142,10 @@ fn parse_pg_version(human_version: &str) -> PgMajorVersion {
.captures(human_version)
{
Some(captures) if captures.len() == 2 => match &captures["major"] {
"14" => return PG14,
"15" => return PG15,
"16" => return PG16,
"17" => return PG17,
"14" => return V14,
"15" => return V15,
"16" => return V16,
"17" => return V17,
_ => {}
},
_ => {}
@@ -145,14 +158,14 @@ fn parse_pg_version(human_version: &str) -> PgMajorVersion {
pub async fn download_extension(
ext_name: &str,
ext_path: &RemotePath,
remote_ext_base_url: &Url,
ext_remote_storage: &str,
pgbin: &str,
) -> Result<u64> {
info!("Download extension {:?} from {:?}", ext_name, ext_path);
// TODO add retry logic
let download_buffer =
match download_extension_tar(remote_ext_base_url, &ext_path.to_string()).await {
match download_extension_tar(ext_remote_storage, &ext_path.to_string()).await {
Ok(buffer) => buffer,
Err(error_message) => {
return Err(anyhow::anyhow!(
@@ -257,14 +270,10 @@ pub fn create_control_files(remote_extensions: &RemoteExtSpec, pgbin: &str) {
}
// Do request to extension storage proxy, e.g.,
// curl http://pg-ext-s3-gateway.pg-ext-s3-gateway.svc.cluster.local/latest/v15/extensions/anon.tar.zst
// curl http://pg-ext-s3-gateway/latest/v15/extensions/anon.tar.zst
// using HTTP GET and return the response body as bytes.
async fn download_extension_tar(remote_ext_base_url: &Url, ext_path: &str) -> Result<Bytes> {
let uri = remote_ext_base_url.join(ext_path).with_context(|| {
format!(
"failed to create the remote extension URI for {ext_path} using {remote_ext_base_url}"
)
})?;
async fn download_extension_tar(ext_remote_storage: &str, ext_path: &str) -> Result<Bytes> {
let uri = format!("{}/{}", ext_remote_storage, ext_path);
let filename = Path::new(ext_path)
.file_name()
.unwrap_or_else(|| std::ffi::OsStr::new("unknown"))
@@ -274,7 +283,7 @@ async fn download_extension_tar(remote_ext_base_url: &Url, ext_path: &str) -> Re
info!("Downloading extension file '{}' from uri {}", filename, uri);
match do_extension_server_request(uri).await {
match do_extension_server_request(&uri).await {
Ok(resp) => {
info!("Successfully downloaded remote extension data {}", ext_path);
REMOTE_EXT_REQUESTS_TOTAL
@@ -293,10 +302,13 @@ async fn download_extension_tar(remote_ext_base_url: &Url, ext_path: &str) -> Re
// Do a single remote extensions server request.
// Return result or (error message + stringified status code) in case of any failures.
async fn do_extension_server_request(uri: Url) -> Result<Bytes, (String, String)> {
async fn do_extension_server_request(uri: &str) -> Result<Bytes, (String, String)> {
let resp = reqwest::get(uri).await.map_err(|e| {
(
format!("could not perform remote extensions server request: {e:?}"),
format!(
"could not perform remote extensions server request: {:?}",
e
),
UNKNOWN_HTTP_STATUS.to_string(),
)
})?;
@@ -306,7 +318,7 @@ async fn do_extension_server_request(uri: Url) -> Result<Bytes, (String, String)
StatusCode::OK => match resp.bytes().await {
Ok(resp) => Ok(resp),
Err(e) => Err((
format!("could not read remote extensions server response: {e:?}"),
format!("could not read remote extensions server response: {:?}", e),
// It's fine to return and report error with status as 200 OK,
// because we still failed to read the response.
status.to_string(),
@@ -317,7 +329,10 @@ async fn do_extension_server_request(uri: Url) -> Result<Bytes, (String, String)
status.to_string(),
)),
_ => Err((
format!("unexpected remote extensions server response status code: {status}"),
format!(
"unexpected remote extensions server response status code: {}",
status
),
status.to_string(),
)),
}
@@ -329,25 +344,25 @@ mod tests {
#[test]
fn test_parse_pg_version() {
use postgres_versioninfo::PgMajorVersion::*;
assert_eq!(parse_pg_version("PostgreSQL 15.4"), PG15);
assert_eq!(parse_pg_version("PostgreSQL 15.14"), PG15);
use super::PostgresMajorVersion::*;
assert_eq!(parse_pg_version("PostgreSQL 15.4"), V15);
assert_eq!(parse_pg_version("PostgreSQL 15.14"), V15);
assert_eq!(
parse_pg_version("PostgreSQL 15.4 (Ubuntu 15.4-0ubuntu0.23.04.1)"),
PG15
V15
);
assert_eq!(parse_pg_version("PostgreSQL 14.15"), PG14);
assert_eq!(parse_pg_version("PostgreSQL 14.0"), PG14);
assert_eq!(parse_pg_version("PostgreSQL 14.15"), V14);
assert_eq!(parse_pg_version("PostgreSQL 14.0"), V14);
assert_eq!(
parse_pg_version("PostgreSQL 14.9 (Debian 14.9-1.pgdg120+1"),
PG14
V14
);
assert_eq!(parse_pg_version("PostgreSQL 16devel"), PG16);
assert_eq!(parse_pg_version("PostgreSQL 16beta1"), PG16);
assert_eq!(parse_pg_version("PostgreSQL 16rc2"), PG16);
assert_eq!(parse_pg_version("PostgreSQL 16extra"), PG16);
assert_eq!(parse_pg_version("PostgreSQL 16devel"), V16);
assert_eq!(parse_pg_version("PostgreSQL 16beta1"), V16);
assert_eq!(parse_pg_version("PostgreSQL 16rc2"), V16);
assert_eq!(parse_pg_version("PostgreSQL 16extra"), V16);
}
#[test]

View File

@@ -1,10 +1,12 @@
use std::collections::HashSet;
use anyhow::{Result, anyhow};
use axum::{RequestExt, body::Body};
use axum_extra::{
TypedHeader,
headers::{Authorization, authorization::Bearer},
};
use compute_api::requests::{COMPUTE_AUDIENCE, ComputeClaims, ComputeClaimsScope};
use compute_api::requests::ComputeClaims;
use futures::future::BoxFuture;
use http::{Request, Response, StatusCode};
use jsonwebtoken::{Algorithm, DecodingKey, TokenData, Validation, jwk::JwkSet};
@@ -23,14 +25,13 @@ pub(in crate::http) struct Authorize {
impl Authorize {
pub fn new(compute_id: String, jwks: JwkSet) -> Self {
let mut validation = Validation::new(Algorithm::EdDSA);
// Nothing is currently required
validation.required_spec_claims = HashSet::new();
validation.validate_exp = true;
// Unused by the control plane
validation.validate_nbf = false;
// Unused by the control plane
validation.validate_aud = false;
validation.set_audience(&[COMPUTE_AUDIENCE]);
// Nothing is currently required
validation.set_required_spec_claims(&[] as &[&str; 0]);
// Unused by the control plane
validation.validate_nbf = false;
Self {
compute_id,
@@ -63,47 +64,11 @@ impl AsyncAuthorizeRequest<Body> for Authorize {
Err(e) => return Err(JsonResponse::error(StatusCode::UNAUTHORIZED, e)),
};
match data.claims.scope {
// TODO: We should validate audience for every token, but
// instead of this ad-hoc validation, we should turn
// [`Validation::validate_aud`] on. This is merely a stopgap
// while we roll out `aud` deployment. We return a 401
// Unauthorized because when we eventually do use
// [`Validation`], we will hit the above `Err` match arm which
// returns 401 Unauthorized.
Some(ComputeClaimsScope::Admin) => {
let Some(ref audience) = data.claims.audience else {
return Err(JsonResponse::error(
StatusCode::UNAUTHORIZED,
"missing audience in authorization token claims",
));
};
if !audience.iter().any(|a| a == COMPUTE_AUDIENCE) {
return Err(JsonResponse::error(
StatusCode::UNAUTHORIZED,
"invalid audience in authorization token claims",
));
}
}
// If the scope is not [`ComputeClaimsScope::Admin`], then we
// must validate the compute_id
_ => {
let Some(ref claimed_compute_id) = data.claims.compute_id else {
return Err(JsonResponse::error(
StatusCode::FORBIDDEN,
"missing compute_id in authorization token claims",
));
};
if *claimed_compute_id != compute_id {
return Err(JsonResponse::error(
StatusCode::FORBIDDEN,
"invalid compute ID in authorization token claims",
));
}
}
if data.claims.compute_id != compute_id {
return Err(JsonResponse::error(
StatusCode::UNAUTHORIZED,
"invalid compute ID in authorization token claims",
));
}
// Make claims available to any subsequent middleware or request

View File

@@ -48,9 +48,11 @@ impl JsonResponse {
/// Create an error response related to the compute being in an invalid state
pub(self) fn invalid_status(status: ComputeStatus) -> Response {
Self::error(
Self::create_response(
StatusCode::PRECONDITION_FAILED,
format!("invalid compute status: {status}"),
&GenericAPIError {
error: format!("invalid compute status: {status}"),
},
)
}
}

View File

@@ -22,7 +22,7 @@ pub(in crate::http) async fn configure(
State(compute): State<Arc<ComputeNode>>,
request: Json<ConfigurationRequest>,
) -> Response {
let pspec = match ParsedSpec::try_from(request.0.spec) {
let pspec = match ParsedSpec::try_from(request.spec.clone()) {
Ok(p) => p,
Err(e) => return JsonResponse::error(StatusCode::BAD_REQUEST, e),
};
@@ -65,7 +65,7 @@ pub(in crate::http) async fn configure(
if state.status == ComputeStatus::Failed {
let err = state.error.as_ref().map_or("unknown error", |x| x);
let msg = format!("compute configuration failed: {err:?}");
let msg = format!("compute configuration failed: {:?}", err);
return Err(msg);
}
}

View File

@@ -22,7 +22,7 @@ pub(in crate::http) async fn download_extension(
State(compute): State<Arc<ComputeNode>>,
) -> Response {
// Don't even try to download extensions if no remote storage is configured
if compute.params.remote_ext_base_url.is_none() {
if compute.params.ext_remote_storage.is_none() {
return JsonResponse::error(
StatusCode::PRECONDITION_FAILED,
"remote storage is not configured",

View File

@@ -1,48 +0,0 @@
use crate::compute_prewarm::LfcPrewarmStateWithProgress;
use crate::http::JsonResponse;
use axum::response::{IntoResponse, Response};
use axum::{Json, http::StatusCode};
use axum_extra::extract::OptionalQuery;
use compute_api::responses::LfcOffloadState;
type Compute = axum::extract::State<std::sync::Arc<crate::compute::ComputeNode>>;
pub(in crate::http) async fn prewarm_state(compute: Compute) -> Json<LfcPrewarmStateWithProgress> {
Json(compute.lfc_prewarm_state().await)
}
// Following functions are marked async for axum, as it's more convenient than wrapping these
// in async lambdas at call site
pub(in crate::http) async fn offload_state(compute: Compute) -> Json<LfcOffloadState> {
Json(compute.lfc_offload_state())
}
#[derive(serde::Deserialize)]
pub struct PrewarmQuery {
pub from_endpoint: String,
}
pub(in crate::http) async fn prewarm(
compute: Compute,
OptionalQuery(query): OptionalQuery<PrewarmQuery>,
) -> Response {
if compute.prewarm_lfc(query.map(|q| q.from_endpoint)) {
StatusCode::ACCEPTED.into_response()
} else {
JsonResponse::error(
StatusCode::TOO_MANY_REQUESTS,
"Multiple requests for prewarm are not allowed",
)
}
}
pub(in crate::http) async fn offload(compute: Compute) -> Response {
if compute.offload_lfc() {
StatusCode::ACCEPTED.into_response()
} else {
JsonResponse::error(
StatusCode::TOO_MANY_REQUESTS,
"Multiple requests for prewarm offload are not allowed",
)
}
}

View File

@@ -11,7 +11,6 @@ pub(in crate::http) mod extensions;
pub(in crate::http) mod failpoints;
pub(in crate::http) mod grants;
pub(in crate::http) mod insights;
pub(in crate::http) mod lfc;
pub(in crate::http) mod metrics;
pub(in crate::http) mod metrics_json;
pub(in crate::http) mod status;

View File

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

View File

@@ -23,7 +23,7 @@ use super::{
middleware::authorize::Authorize,
routes::{
check_writability, configure, database_schema, dbs_and_roles, extension_server, extensions,
grants, insights, lfc, metrics, metrics_json, status, terminate,
grants, insights, metrics, metrics_json, status, terminate,
},
};
use crate::compute::ComputeNode;
@@ -85,8 +85,6 @@ impl From<&Server> for Router<Arc<ComputeNode>> {
Router::<Arc<ComputeNode>>::new().route("/metrics", get(metrics::get_metrics));
let authenticated_router = Router::<Arc<ComputeNode>>::new()
.route("/lfc/prewarm", get(lfc::prewarm_state).post(lfc::prewarm))
.route("/lfc/offload", get(lfc::offload_state).post(lfc::offload))
.route("/check_writability", post(check_writability::is_writable))
.route("/configure", post(configure::configure))
.route("/database_schema", get(database_schema::get_schema_dump))

View File

@@ -43,7 +43,7 @@ pub async fn get_installed_extensions(mut conf: Config) -> Result<InstalledExten
let (mut client, connection) = conf.connect(NoTls).await?;
tokio::spawn(async move {
if let Err(e) = connection.await {
eprintln!("connection error: {e}");
eprintln!("connection error: {}", e);
}
});
@@ -57,7 +57,7 @@ pub async fn get_installed_extensions(mut conf: Config) -> Result<InstalledExten
let (client, connection) = conf.connect(NoTls).await?;
tokio::spawn(async move {
if let Err(e) = connection.await {
eprintln!("connection error: {e}");
eprintln!("connection error: {}", e);
}
});

View File

@@ -11,7 +11,6 @@ pub mod http;
pub mod logger;
pub mod catalog;
pub mod compute;
pub mod compute_prewarm;
pub mod disk_quota;
pub mod extension_server;
pub mod installed_extensions;
@@ -22,7 +21,6 @@ mod migration;
pub mod monitor;
pub mod params;
pub mod pg_helpers;
pub mod pgbouncer;
pub mod rsyslog;
pub mod spec;
mod spec_apply;

View File

@@ -130,7 +130,7 @@ fn try_acquire_lsn_lease(
lsn: Lsn,
) -> Result<Option<SystemTime>> {
let mut client = config.connect(NoTls)?;
let cmd = format!("lease lsn {tenant_shard_id} {timeline_id} {lsn} ");
let cmd = format!("lease lsn {} {} {} ", tenant_shard_id, timeline_id, lsn);
let res = client.simple_query(&cmd)?;
let msg = match res.first() {
Some(msg) => msg,

View File

@@ -1,7 +1,7 @@
use metrics::core::{AtomicF64, AtomicU64, Collector, GenericCounter, GenericGauge};
use metrics::proto::MetricFamily;
use metrics::{
IntCounter, IntCounterVec, IntGaugeVec, UIntGaugeVec, register_gauge, register_int_counter,
IntCounterVec, IntGaugeVec, UIntGaugeVec, register_gauge, register_int_counter,
register_int_counter_vec, register_int_gauge_vec, register_uint_gauge_vec,
};
use once_cell::sync::Lazy;
@@ -97,24 +97,6 @@ pub(crate) static PG_TOTAL_DOWNTIME_MS: Lazy<GenericCounter<AtomicU64>> = Lazy::
.expect("failed to define a metric")
});
/// Needed as neon.file_cache_prewarm_batch == 0 doesn't mean we never tried to prewarm.
/// On the other hand, LFC_PREWARMED_PAGES is excessive as we can GET /lfc/prewarm
pub(crate) static LFC_PREWARM_REQUESTS: Lazy<IntCounter> = Lazy::new(|| {
register_int_counter!(
"compute_ctl_lfc_prewarm_requests_total",
"Total number of LFC prewarm requests made by compute_ctl",
)
.expect("failed to define a metric")
});
pub(crate) static LFC_OFFLOAD_REQUESTS: Lazy<IntCounter> = Lazy::new(|| {
register_int_counter!(
"compute_ctl_lfc_offload_requests_total",
"Total number of LFC offload requests made by compute_ctl",
)
.expect("failed to define a metric")
});
pub fn collect() -> Vec<MetricFamily> {
let mut metrics = COMPUTE_CTL_UP.collect();
metrics.extend(INSTALLED_EXTENSIONS.collect());
@@ -124,7 +106,5 @@ pub fn collect() -> Vec<MetricFamily> {
metrics.extend(AUDIT_LOG_DIR_SIZE.collect());
metrics.extend(PG_CURR_DOWNTIME_MS.collect());
metrics.extend(PG_TOTAL_DOWNTIME_MS.collect());
metrics.extend(LFC_PREWARM_REQUESTS.collect());
metrics.extend(LFC_OFFLOAD_REQUESTS.collect());
metrics
}

View File

@@ -13,12 +13,6 @@ use crate::metrics::{PG_CURR_DOWNTIME_MS, PG_TOTAL_DOWNTIME_MS};
const MONITOR_CHECK_INTERVAL: Duration = Duration::from_millis(500);
/// Struct to store runtime state of the compute monitor thread.
/// In theory, this could be a part of `Compute`, but i)
/// this state is expected to be accessed only by single thread,
/// so we don't need to care about locking; ii) `Compute` is
/// already quite big. Thus, it seems to be a good idea to keep
/// all the activity/health monitoring parts here.
struct ComputeMonitor {
compute: Arc<ComputeNode>,
@@ -76,38 +70,12 @@ impl ComputeMonitor {
)
}
/// Check if compute is in some terminal or soon-to-be-terminal
/// state, then return `true`, signalling the caller that it
/// should exit gracefully. Otherwise, return `false`.
fn check_interrupts(&mut self) -> bool {
let compute_status = self.compute.get_status();
if matches!(
compute_status,
ComputeStatus::Terminated
| ComputeStatus::TerminationPending { .. }
| ComputeStatus::Failed
) {
info!(
"compute is in {} status, stopping compute monitor",
compute_status
);
return true;
}
false
}
/// Spin in a loop and figure out the last activity time in the Postgres.
/// Then update it in the shared state. This function currently never
/// errors out explicitly, but there is a graceful termination path.
/// Every time we receive an error trying to check Postgres, we use
/// [`ComputeMonitor::check_interrupts()`] because it could be that
/// compute is being terminated already, then we can exit gracefully
/// to not produce errors' noise in the log.
/// Then update it in the shared state. This function never errors out.
/// NB: the only expected panic is at `Mutex` unwrap(), all other errors
/// should be handled gracefully.
#[instrument(skip_all)]
pub fn run(&mut self) -> anyhow::Result<()> {
pub fn run(&mut self) {
// Suppose that `connstr` doesn't change
let connstr = self.compute.params.connstr.clone();
let conf = self
@@ -125,10 +93,6 @@ impl ComputeMonitor {
info!("starting compute monitor for {}", connstr);
loop {
if self.check_interrupts() {
break;
}
match &mut client {
Ok(cli) => {
if cli.is_closed() {
@@ -136,10 +100,6 @@ impl ComputeMonitor {
downtime_info = self.downtime_info(),
"connection to Postgres is closed, trying to reconnect"
);
if self.check_interrupts() {
break;
}
self.report_down();
// Connection is closed, reconnect and try again.
@@ -151,19 +111,15 @@ impl ComputeMonitor {
self.compute.update_last_active(self.last_active);
}
Err(e) => {
error!(
downtime_info = self.downtime_info(),
"could not check Postgres: {}", e
);
if self.check_interrupts() {
break;
}
// Although we have many places where we can return errors in `check()`,
// normally it shouldn't happen. I.e., we will likely return error if
// connection got broken, query timed out, Postgres returned invalid data, etc.
// In all such cases it's suspicious, so let's report this as downtime.
self.report_down();
error!(
downtime_info = self.downtime_info(),
"could not check Postgres: {}", e
);
// Reconnect to Postgres just in case. During tests, I noticed
// that queries in `check()` can fail with `connection closed`,
@@ -180,10 +136,6 @@ impl ComputeMonitor {
downtime_info = self.downtime_info(),
"could not connect to Postgres: {}, retrying", e
);
if self.check_interrupts() {
break;
}
self.report_down();
// Establish a new connection and try again.
@@ -195,9 +147,6 @@ impl ComputeMonitor {
self.last_checked = Utc::now();
thread::sleep(MONITOR_CHECK_INTERVAL);
}
// Graceful termination path
Ok(())
}
#[instrument(skip_all)]
@@ -475,15 +424,12 @@ pub fn launch_monitor(compute: &Arc<ComputeNode>) -> thread::JoinHandle<()> {
experimental,
};
let span = span!(Level::INFO, "compute_monitor");
thread::Builder::new()
.name("compute-monitor".into())
.spawn(move || {
let span = span!(Level::INFO, "compute_monitor");
let _enter = span.enter();
match monitor.run() {
Ok(_) => info!("compute monitor thread terminated gracefully"),
Err(err) => error!("compute monitor thread terminated abnormally {:?}", err),
}
monitor.run();
})
.expect("cannot launch compute monitor thread")
}

View File

@@ -36,9 +36,9 @@ pub fn escape_literal(s: &str) -> String {
let res = s.replace('\'', "''").replace('\\', "\\\\");
if res.contains('\\') {
format!("E'{res}'")
format!("E'{}'", res)
} else {
format!("'{res}'")
format!("'{}'", res)
}
}
@@ -46,7 +46,7 @@ pub fn escape_literal(s: &str) -> String {
/// with `'{}'` is not required, as it returns a ready-to-use config string.
pub fn escape_conf_value(s: &str) -> String {
let res = s.replace('\'', "''").replace('\\', "\\\\");
format!("'{res}'")
format!("'{}'", res)
}
pub trait GenericOptionExt {
@@ -213,10 +213,8 @@ impl Escaping for PgIdent {
// Find the first suitable tag that is not present in the string.
// Postgres' max role/DB name length is 63 bytes, so even in the
// worst case it won't take long. Outer tag is always `tag + "x"`,
// so if `tag` is not present in the string, `outer_tag` is not
// present in the string either.
while self.contains(&tag.to_string()) {
// worst case it won't take long.
while self.contains(&format!("${tag}$")) || self.contains(&format!("${outer_tag}$")) {
tag += "x";
outer_tag = tag.clone() + "x";
}
@@ -446,7 +444,7 @@ pub async fn tune_pgbouncer(
let mut pgbouncer_connstr =
"host=localhost port=6432 dbname=pgbouncer user=postgres sslmode=disable".to_string();
if let Ok(pass) = std::env::var("PGBOUNCER_PASSWORD") {
pgbouncer_connstr.push_str(format!(" password={pass}").as_str());
pgbouncer_connstr.push_str(format!(" password={}", pass).as_str());
}
pgbouncer_connstr
};
@@ -464,7 +462,7 @@ pub async fn tune_pgbouncer(
Ok((client, connection)) => {
tokio::spawn(async move {
if let Err(e) = connection.await {
eprintln!("connection error: {e}");
eprintln!("connection error: {}", e);
}
});
break client;

View File

@@ -1 +0,0 @@
pub const PGBOUNCER_PIDFILE: &str = "/tmp/pgbouncer.pid";

View File

@@ -27,40 +27,6 @@ fn get_rsyslog_pid() -> Option<String> {
}
}
fn wait_for_rsyslog_pid() -> Result<String, anyhow::Error> {
const MAX_WAIT: Duration = Duration::from_secs(5);
const INITIAL_SLEEP: Duration = Duration::from_millis(2);
let mut sleep_duration = INITIAL_SLEEP;
let start = std::time::Instant::now();
let mut attempts = 1;
for attempt in 1.. {
attempts = attempt;
match get_rsyslog_pid() {
Some(pid) => return Ok(pid),
None => {
if start.elapsed() >= MAX_WAIT {
break;
}
info!(
"rsyslogd is not running, attempt {}. Sleeping for {} ms",
attempt,
sleep_duration.as_millis()
);
std::thread::sleep(sleep_duration);
sleep_duration *= 2;
}
}
}
Err(anyhow::anyhow!(
"rsyslogd is not running after waiting for {} seconds and {} attempts",
attempts,
start.elapsed().as_secs()
))
}
// Restart rsyslogd to apply the new configuration.
// This is necessary, because there is no other way to reload the rsyslog configuration.
//
@@ -70,29 +36,27 @@ fn wait_for_rsyslog_pid() -> Result<String, anyhow::Error> {
// TODO: test it properly
//
fn restart_rsyslog() -> Result<()> {
let old_pid = get_rsyslog_pid().context("rsyslogd is not running")?;
info!("rsyslogd is running with pid: {}, restart it", old_pid);
// kill it to restart
let _ = Command::new("pkill")
.arg("rsyslogd")
.output()
.context("Failed to restart rsyslogd")?;
// ensure rsyslogd is running
wait_for_rsyslog_pid()?;
.context("Failed to stop rsyslogd")?;
Ok(())
}
pub fn configure_audit_rsyslog(
log_directory: String,
endpoint_id: &str,
project_id: &str,
tag: Option<String>,
remote_endpoint: &str,
) -> Result<()> {
let config_content: String = format!(
include_str!("config_template/compute_audit_rsyslog_template.conf"),
log_directory = log_directory,
endpoint_id = endpoint_id,
project_id = project_id,
tag = tag.unwrap_or("".to_string()),
remote_endpoint = remote_endpoint
);
@@ -167,11 +131,15 @@ pub fn configure_postgres_logs_export(conf: PostgresLogsRsyslogConfig) -> Result
return Ok(());
}
// Nothing to configure
// When new config is empty we can simply remove the configuration file.
if new_config.is_empty() {
// When the configuration is removed, PostgreSQL will stop sending data
// to the files watched by rsyslog, so restarting rsyslog is more effort
// than just ignoring this change.
info!("removing rsyslog config file: {}", POSTGRES_LOGS_CONF_PATH);
match std::fs::remove_file(POSTGRES_LOGS_CONF_PATH) {
Ok(_) => {}
Err(err) if err.kind() == ErrorKind::NotFound => {}
Err(err) => return Err(err.into()),
}
restart_rsyslog()?;
return Ok(());
}

View File

@@ -23,12 +23,12 @@ fn do_control_plane_request(
) -> Result<ControlPlaneConfigResponse, (bool, String, String)> {
let resp = reqwest::blocking::Client::new()
.get(uri)
.header("Authorization", format!("Bearer {jwt}"))
.header("Authorization", format!("Bearer {}", jwt))
.send()
.map_err(|e| {
(
true,
format!("could not perform request to control plane: {e:?}"),
format!("could not perform request to control plane: {:?}", e),
UNKNOWN_HTTP_STATUS.to_string(),
)
})?;
@@ -39,7 +39,7 @@ fn do_control_plane_request(
Ok(spec_resp) => Ok(spec_resp),
Err(e) => Err((
true,
format!("could not deserialize control plane response: {e:?}"),
format!("could not deserialize control plane response: {:?}", e),
status.to_string(),
)),
},
@@ -62,7 +62,7 @@ fn do_control_plane_request(
// or some internal failure happened. Doesn't make much sense to retry in this case.
_ => Err((
false,
format!("unexpected control plane response status code: {status}"),
format!("unexpected control plane response status code: {}", status),
status.to_string(),
)),
}

View File

@@ -933,53 +933,56 @@ async fn get_operations<'a>(
PerDatabasePhase::DeleteDBRoleReferences => {
let ctx = ctx.read().await;
let operations = spec
.delta_operations
.iter()
.flatten()
.filter(|op| op.action == "delete_role")
.filter_map(move |op| {
if db.is_owned_by(&op.name) {
return None;
}
if !ctx.roles.contains_key(&op.name) {
return None;
}
let quoted = op.name.pg_quote();
let new_owner = match &db {
DB::SystemDB => PgIdent::from("cloud_admin").pg_quote(),
DB::UserDB(db) => db.owner.pg_quote(),
};
let (escaped_role, outer_tag) = op.name.pg_quote_dollar();
let operations =
spec.delta_operations
.iter()
.flatten()
.filter(|op| op.action == "delete_role")
.filter_map(move |op| {
if db.is_owned_by(&op.name) {
return None;
}
if !ctx.roles.contains_key(&op.name) {
return None;
}
let quoted = op.name.pg_quote();
let new_owner = match &db {
DB::SystemDB => PgIdent::from("cloud_admin").pg_quote(),
DB::UserDB(db) => db.owner.pg_quote(),
};
let (escaped_role, outer_tag) = op.name.pg_quote_dollar();
Some(vec![
// This will reassign all dependent objects to the db owner
Operation {
query: format!("REASSIGN OWNED BY {quoted} TO {new_owner}",),
comment: None,
},
// Revoke some potentially blocking privileges (Neon-specific currently)
Operation {
query: format!(
include_str!("sql/pre_drop_role_revoke_privileges.sql"),
// N.B. this has to be properly dollar-escaped with `pg_quote_dollar()`
role_name = escaped_role,
outer_tag = outer_tag,
),
comment: None,
},
// This now will only drop privileges of the role
// TODO: this is obviously not 100% true because of the above case,
// there could be still some privileges that are not revoked. Maybe this
// only drops privileges that were granted *by this* role, not *to this* role,
// but this has to be checked.
Operation {
query: format!("DROP OWNED BY {quoted}"),
comment: None,
},
])
})
.flatten();
Some(vec![
// This will reassign all dependent objects to the db owner
Operation {
query: format!(
"REASSIGN OWNED BY {} TO {}",
quoted, new_owner,
),
comment: None,
},
// Revoke some potentially blocking privileges (Neon-specific currently)
Operation {
query: format!(
include_str!("sql/pre_drop_role_revoke_privileges.sql"),
// N.B. this has to be properly dollar-escaped with `pg_quote_dollar()`
role_name = escaped_role,
outer_tag = outer_tag,
),
comment: None,
},
// This now will only drop privileges of the role
// TODO: this is obviously not 100% true because of the above case,
// there could be still some privileges that are not revoked. Maybe this
// only drops privileges that were granted *by this* role, not *to this* role,
// but this has to be checked.
Operation {
query: format!("DROP OWNED BY {}", quoted),
comment: None,
},
])
})
.flatten();
Ok(Box::new(operations))
}

View File

@@ -27,7 +27,7 @@ pub async fn ping_safekeeper(
let (client, conn) = config.connect(tokio_postgres::NoTls).await?;
tokio::spawn(async move {
if let Err(e) = conn.await {
eprintln!("connection error: {e}");
eprintln!("connection error: {}", e);
}
});

View File

@@ -1,6 +0,0 @@
### Test files
The file `cluster_spec.json` has been copied over from libs/compute_api
tests, with some edits:
- the neon.safekeepers setting contains a duplicate value

View File

@@ -1,245 +0,0 @@
{
"format_version": 1.0,
"timestamp": "2021-05-23T18:25:43.511Z",
"operation_uuid": "0f657b36-4b0f-4a2d-9c2e-1dcd615e7d8b",
"cluster": {
"cluster_id": "test-cluster-42",
"name": "Zenith Test",
"state": "restarted",
"roles": [
{
"name": "postgres",
"encrypted_password": "6b1d16b78004bbd51fa06af9eda75972",
"options": null
},
{
"name": "alexk",
"encrypted_password": null,
"options": null
},
{
"name": "zenith \"new\"",
"encrypted_password": "5b1d16b78004bbd51fa06af9eda75972",
"options": null
},
{
"name": "zen",
"encrypted_password": "9b1d16b78004bbd51fa06af9eda75972"
},
{
"name": "\"name\";\\n select 1;",
"encrypted_password": "5b1d16b78004bbd51fa06af9eda75972"
},
{
"name": "MyRole",
"encrypted_password": "5b1d16b78004bbd51fa06af9eda75972"
}
],
"databases": [
{
"name": "DB2",
"owner": "alexk",
"options": [
{
"name": "LC_COLLATE",
"value": "C",
"vartype": "string"
},
{
"name": "LC_CTYPE",
"value": "C",
"vartype": "string"
},
{
"name": "TEMPLATE",
"value": "template0",
"vartype": "enum"
}
]
},
{
"name": "zenith",
"owner": "MyRole"
},
{
"name": "zen",
"owner": "zen"
}
],
"settings": [
{
"name": "fsync",
"value": "off",
"vartype": "bool"
},
{
"name": "wal_level",
"value": "logical",
"vartype": "enum"
},
{
"name": "hot_standby",
"value": "on",
"vartype": "bool"
},
{
"name": "prewarm_lfc_on_startup",
"value": "off",
"vartype": "bool"
},
{
"name": "neon.safekeepers",
"value": "127.0.0.1:6502,127.0.0.1:6503,127.0.0.1:6501,127.0.0.1:6502",
"vartype": "string"
},
{
"name": "wal_log_hints",
"value": "on",
"vartype": "bool"
},
{
"name": "log_connections",
"value": "on",
"vartype": "bool"
},
{
"name": "shared_buffers",
"value": "32768",
"vartype": "integer"
},
{
"name": "port",
"value": "55432",
"vartype": "integer"
},
{
"name": "max_connections",
"value": "100",
"vartype": "integer"
},
{
"name": "max_wal_senders",
"value": "10",
"vartype": "integer"
},
{
"name": "listen_addresses",
"value": "0.0.0.0",
"vartype": "string"
},
{
"name": "wal_sender_timeout",
"value": "0",
"vartype": "integer"
},
{
"name": "password_encryption",
"value": "md5",
"vartype": "enum"
},
{
"name": "maintenance_work_mem",
"value": "65536",
"vartype": "integer"
},
{
"name": "max_parallel_workers",
"value": "8",
"vartype": "integer"
},
{
"name": "max_worker_processes",
"value": "8",
"vartype": "integer"
},
{
"name": "neon.tenant_id",
"value": "b0554b632bd4d547a63b86c3630317e8",
"vartype": "string"
},
{
"name": "max_replication_slots",
"value": "10",
"vartype": "integer"
},
{
"name": "neon.timeline_id",
"value": "2414a61ffc94e428f14b5758fe308e13",
"vartype": "string"
},
{
"name": "shared_preload_libraries",
"value": "neon",
"vartype": "string"
},
{
"name": "synchronous_standby_names",
"value": "walproposer",
"vartype": "string"
},
{
"name": "neon.pageserver_connstring",
"value": "host=127.0.0.1 port=6400",
"vartype": "string"
},
{
"name": "test.escaping",
"value": "here's a backslash \\ and a quote ' and a double-quote \" hooray",
"vartype": "string"
}
]
},
"delta_operations": [
{
"action": "delete_db",
"name": "zenith_test"
},
{
"action": "rename_db",
"name": "DB",
"new_name": "DB2"
},
{
"action": "delete_role",
"name": "zenith2"
},
{
"action": "rename_role",
"name": "zenith new",
"new_name": "zenith \"new\""
}
],
"remote_extensions": {
"library_index": {
"postgis-3": "postgis",
"libpgrouting-3.4": "postgis",
"postgis_raster-3": "postgis",
"postgis_sfcgal-3": "postgis",
"postgis_topology-3": "postgis",
"address_standardizer-3": "postgis"
},
"extension_data": {
"postgis": {
"archive_path": "5834329303/v15/extensions/postgis.tar.zst",
"control_data": {
"postgis.control": "# postgis extension\ncomment = ''PostGIS geometry and geography spatial types and functions''\ndefault_version = ''3.3.2''\nmodule_pathname = ''$libdir/postgis-3''\nrelocatable = false\ntrusted = true\n",
"pgrouting.control": "# pgRouting Extension\ncomment = ''pgRouting Extension''\ndefault_version = ''3.4.2''\nmodule_pathname = ''$libdir/libpgrouting-3.4''\nrelocatable = true\nrequires = ''plpgsql''\nrequires = ''postgis''\ntrusted = true\n",
"postgis_raster.control": "# postgis_raster extension\ncomment = ''PostGIS raster types and functions''\ndefault_version = ''3.3.2''\nmodule_pathname = ''$libdir/postgis_raster-3''\nrelocatable = false\nrequires = postgis\ntrusted = true\n",
"postgis_sfcgal.control": "# postgis topology extension\ncomment = ''PostGIS SFCGAL functions''\ndefault_version = ''3.3.2''\nrelocatable = true\nrequires = postgis\ntrusted = true\n",
"postgis_topology.control": "# postgis topology extension\ncomment = ''PostGIS topology spatial types and functions''\ndefault_version = ''3.3.2''\nrelocatable = false\nschema = topology\nrequires = postgis\ntrusted = true\n",
"address_standardizer.control": "# address_standardizer extension\ncomment = ''Used to parse an address into constituent elements. Generally used to support geocoding address normalization step.''\ndefault_version = ''3.3.2''\nrelocatable = true\ntrusted = true\n",
"postgis_tiger_geocoder.control": "# postgis tiger geocoder extension\ncomment = ''PostGIS tiger geocoder and reverse geocoder''\ndefault_version = ''3.3.2''\nrelocatable = false\nschema = tiger\nrequires = ''postgis,fuzzystrmatch''\nsuperuser= false\ntrusted = true\n",
"address_standardizer_data_us.control": "# address standardizer us dataset\ncomment = ''Address Standardizer US dataset example''\ndefault_version = ''3.3.2''\nrelocatable = true\ntrusted = true\n"
}
}
},
"custom_extensions": [],
"public_extensions": ["postgis"]
},
"pgbouncer_settings": {
"default_pool_size": "42",
"pool_mode": "session"
}
}

View File

@@ -30,7 +30,6 @@ mod pg_helpers_tests {
r#"fsync = off
wal_level = logical
hot_standby = on
autoprewarm = off
neon.safekeepers = '127.0.0.1:6502,127.0.0.1:6503,127.0.0.1:6501'
wal_log_hints = on
log_connections = on
@@ -71,14 +70,6 @@ test.escaping = 'here''s a backslash \\ and a quote '' and a double-quote " hoor
("name$$$", ("$x$name$$$$x$", "xx")),
("name$$$$", ("$x$name$$$$$x$", "xx")),
("name$x$", ("$xx$name$x$$xx$", "xxx")),
("x", ("$xx$x$xx$", "xxx")),
("xx", ("$xxx$xx$xxx$", "xxxx")),
("$x", ("$xx$$x$xx$", "xxx")),
("x$", ("$xx$x$$xx$", "xxx")),
("$x$", ("$xx$$x$$xx$", "xxx")),
("xx$", ("$xxx$xx$$xxx$", "xxxx")),
("$xx", ("$xxx$$xx$xxx$", "xxxx")),
("$xx$", ("$xxx$$xx$$xxx$", "xxxx")),
];
for (input, expected) in test_cases {

View File

@@ -36,13 +36,12 @@ pageserver_api.workspace = true
pageserver_client.workspace = true
postgres_backend.workspace = true
safekeeper_api.workspace = true
safekeeper_client.workspace = true
postgres_connection.workspace = true
storage_broker.workspace = true
http-utils.workspace = true
utils.workspace = true
whoami.workspace = true
endpoint_storage.workspace = true
compute_api.workspace = true
workspace_hack.workspace = true
tracing.workspace = true

View File

@@ -2,10 +2,8 @@
[pageserver]
listen_pg_addr = '127.0.0.1:64000'
listen_http_addr = '127.0.0.1:9898'
listen_grpc_addr = '127.0.0.1:51051'
pg_auth_type = 'Trust'
http_auth_type = 'Trust'
grpc_auth_type = 'Trust'
[[safekeepers]]
id = 1

View File

@@ -4,10 +4,8 @@
id=1
listen_pg_addr = '127.0.0.1:64000'
listen_http_addr = '127.0.0.1:9898'
listen_grpc_addr = '127.0.0.1:51051'
pg_auth_type = 'Trust'
http_auth_type = 'Trust'
grpc_auth_type = 'Trust'
[[safekeepers]]
id = 1

View File

@@ -14,7 +14,7 @@
use std::ffi::OsStr;
use std::io::Write;
use std::os::fd::AsFd;
use std::os::unix::prelude::AsRawFd;
use std::os::unix::process::CommandExt;
use std::path::Path;
use std::process::Command;
@@ -356,7 +356,7 @@ where
let file = pid_file::claim_for_current_process(&path).expect("claim pid file");
// Remove the FD_CLOEXEC flag on the pidfile descriptor so that the pidfile
// remains locked after exec.
nix::fcntl::fcntl(file.as_fd(), FcntlArg::F_SETFD(FdFlag::empty()))
nix::fcntl::fcntl(file.as_raw_fd(), FcntlArg::F_SETFD(FdFlag::empty()))
.expect("remove FD_CLOEXEC");
// Don't run drop(file), it would close the file before we actually exec.
std::mem::forget(file);

View File

@@ -8,6 +8,7 @@
use std::borrow::Cow;
use std::collections::{BTreeSet, HashMap};
use std::fs::File;
use std::os::fd::AsRawFd;
use std::path::PathBuf;
use std::process::exit;
use std::str::FromStr;
@@ -15,12 +16,9 @@ use std::time::Duration;
use anyhow::{Context, Result, anyhow, bail};
use clap::Parser;
use compute_api::requests::ComputeClaimsScope;
use compute_api::spec::ComputeMode;
use control_plane::broker::StorageBroker;
use control_plane::endpoint::{ComputeControlPlane, EndpointTerminateMode, PageserverProtocol};
use control_plane::endpoint_storage::{ENDPOINT_STORAGE_DEFAULT_ADDR, EndpointStorage};
use control_plane::local_env;
use control_plane::endpoint::ComputeControlPlane;
use control_plane::endpoint_storage::{ENDPOINT_STORAGE_DEFAULT_PORT, EndpointStorage};
use control_plane::local_env::{
EndpointStorageConf, InitForceMode, LocalEnv, NeonBroker, NeonLocalInitConf,
NeonLocalInitPageserverConf, SafekeeperConf,
@@ -30,9 +28,9 @@ use control_plane::safekeeper::SafekeeperNode;
use control_plane::storage_controller::{
NeonStorageControllerStartArgs, NeonStorageControllerStopArgs, StorageController,
};
use nix::fcntl::{Flock, FlockArg};
use control_plane::{broker, local_env};
use nix::fcntl::{FlockArg, flock};
use pageserver_api::config::{
DEFAULT_GRPC_LISTEN_PORT as DEFAULT_PAGESERVER_GRPC_PORT,
DEFAULT_HTTP_LISTEN_PORT as DEFAULT_PAGESERVER_HTTP_PORT,
DEFAULT_PG_LISTEN_PORT as DEFAULT_PAGESERVER_PG_PORT,
};
@@ -45,10 +43,10 @@ use pageserver_api::models::{
use pageserver_api::shard::{DEFAULT_STRIPE_SIZE, ShardCount, ShardStripeSize, TenantShardId};
use postgres_backend::AuthType;
use postgres_connection::parse_host_port;
use safekeeper_api::membership::{SafekeeperGeneration, SafekeeperId};
use safekeeper_api::membership::SafekeeperGeneration;
use safekeeper_api::{
DEFAULT_HTTP_LISTEN_PORT as DEFAULT_SAFEKEEPER_HTTP_PORT,
DEFAULT_PG_LISTEN_PORT as DEFAULT_SAFEKEEPER_PG_PORT, PgMajorVersion, PgVersionId,
DEFAULT_PG_LISTEN_PORT as DEFAULT_SAFEKEEPER_PG_PORT,
};
use storage_broker::DEFAULT_LISTEN_ADDR as DEFAULT_BROKER_ADDR;
use tokio::task::JoinSet;
@@ -64,7 +62,7 @@ const DEFAULT_PAGESERVER_ID: NodeId = NodeId(1);
const DEFAULT_BRANCH_NAME: &str = "main";
project_git_version!(GIT_VERSION);
const DEFAULT_PG_VERSION: PgMajorVersion = PgMajorVersion::PG17;
const DEFAULT_PG_VERSION: u32 = 17;
const DEFAULT_PAGESERVER_CONTROL_PLANE_API: &str = "http://127.0.0.1:1234/upcall/v1/";
@@ -169,7 +167,7 @@ struct TenantCreateCmdArgs {
#[arg(default_value_t = DEFAULT_PG_VERSION)]
#[clap(long, help = "Postgres version to use for the initial timeline")]
pg_version: PgMajorVersion,
pg_version: u32,
#[clap(
long,
@@ -292,7 +290,7 @@ struct TimelineCreateCmdArgs {
#[arg(default_value_t = DEFAULT_PG_VERSION)]
#[clap(long, help = "Postgres version")]
pg_version: PgMajorVersion,
pg_version: u32,
}
#[derive(clap::Args)]
@@ -324,7 +322,7 @@ struct TimelineImportCmdArgs {
#[arg(default_value_t = DEFAULT_PG_VERSION)]
#[clap(long, help = "Postgres version of the backup being imported")]
pg_version: PgMajorVersion,
pg_version: u32,
}
#[derive(clap::Subcommand)]
@@ -603,15 +601,7 @@ struct EndpointCreateCmdArgs {
#[arg(default_value_t = DEFAULT_PG_VERSION)]
#[clap(long, help = "Postgres version")]
pg_version: PgMajorVersion,
/// Use gRPC to communicate with Pageservers, by generating grpc:// connstrings.
///
/// Specified on creation such that it's retained across reconfiguration and restarts.
///
/// NB: not yet supported by computes.
#[clap(long)]
grpc: bool,
pg_version: u32,
#[clap(
long,
@@ -652,10 +642,9 @@ struct EndpointStartCmdArgs {
#[clap(
long,
help = "Configure the remote extensions storage proxy gateway URL to request for extensions.",
alias = "remote-ext-config"
help = "Configure the remote extensions storage proxy gateway to request for extensions."
)]
remote_ext_base_url: Option<String>,
remote_ext_config: Option<String>,
#[clap(
long,
@@ -672,13 +661,6 @@ struct EndpointStartCmdArgs {
#[clap(short = 't', long, value_parser= humantime::parse_duration, help = "timeout until we fail the command")]
#[arg(default_value = "90s")]
start_timeout: Duration,
#[clap(
long,
help = "Run in development mode, skipping VM-specific operations like process termination",
action = clap::ArgAction::SetTrue
)]
dev: bool,
}
#[derive(clap::Args)]
@@ -711,9 +693,10 @@ struct EndpointStopCmdArgs {
)]
destroy: bool,
#[clap(long, help = "Postgres shutdown mode")]
#[clap(default_value = "fast")]
mode: EndpointTerminateMode,
#[clap(long, help = "Postgres shutdown mode, passed to \"pg_ctl -m <mode>\"")]
#[arg(value_parser(["smart", "fast", "immediate"]))]
#[arg(default_value = "fast")]
mode: String,
}
#[derive(clap::Args)]
@@ -721,9 +704,6 @@ struct EndpointStopCmdArgs {
struct EndpointGenerateJwtCmdArgs {
#[clap(help = "Postgres endpoint id")]
endpoint_id: String,
#[clap(short = 's', long, help = "Scope to generate the JWT with", value_parser = ComputeClaimsScope::from_str)]
scope: Option<ComputeClaimsScope>,
}
#[derive(clap::Subcommand)]
@@ -763,16 +743,16 @@ struct TimelineTreeEl {
/// A flock-based guard over the neon_local repository directory
struct RepoLock {
_file: Flock<File>,
_file: File,
}
impl RepoLock {
fn new() -> Result<Self> {
let repo_dir = File::open(local_env::base_path())?;
match Flock::lock(repo_dir, FlockArg::LockExclusive) {
Ok(f) => Ok(Self { _file: f }),
Err((_, e)) => Err(e).context("flock error"),
}
let repo_dir_fd = repo_dir.as_raw_fd();
flock(repo_dir_fd, FlockArg::LockExclusive)?;
Ok(Self { _file: repo_dir })
}
}
@@ -919,7 +899,7 @@ fn print_timeline(
br_sym = "┗━";
}
print!("{br_sym} @{ancestor_lsn}: ");
print!("{} @{}: ", br_sym, ancestor_lsn);
}
// Finally print a timeline id and name with new line
@@ -1008,8 +988,7 @@ fn handle_init(args: &InitCmdArgs) -> anyhow::Result<LocalEnv> {
NeonLocalInitConf {
control_plane_api: Some(DEFAULT_PAGESERVER_CONTROL_PLANE_API.parse().unwrap()),
broker: NeonBroker {
listen_addr: Some(DEFAULT_BROKER_ADDR.parse().unwrap()),
listen_https_addr: None,
listen_addr: DEFAULT_BROKER_ADDR.parse().unwrap(),
},
safekeepers: vec![SafekeeperConf {
id: DEFAULT_SAFEKEEPER_ID,
@@ -1022,16 +1001,13 @@ fn handle_init(args: &InitCmdArgs) -> anyhow::Result<LocalEnv> {
let pageserver_id = NodeId(DEFAULT_PAGESERVER_ID.0 + i as u64);
let pg_port = DEFAULT_PAGESERVER_PG_PORT + i;
let http_port = DEFAULT_PAGESERVER_HTTP_PORT + i;
let grpc_port = DEFAULT_PAGESERVER_GRPC_PORT + i;
NeonLocalInitPageserverConf {
id: pageserver_id,
listen_pg_addr: format!("127.0.0.1:{pg_port}"),
listen_http_addr: format!("127.0.0.1:{http_port}"),
listen_https_addr: None,
listen_grpc_addr: Some(format!("127.0.0.1:{grpc_port}")),
pg_auth_type: AuthType::Trust,
http_auth_type: AuthType::Trust,
grpc_auth_type: AuthType::Trust,
other: Default::default(),
// Typical developer machines use disks with slow fsync, and we don't care
// about data integrity: disable disk syncs.
@@ -1040,7 +1016,7 @@ fn handle_init(args: &InitCmdArgs) -> anyhow::Result<LocalEnv> {
})
.collect(),
endpoint_storage: EndpointStorageConf {
listen_addr: ENDPOINT_STORAGE_DEFAULT_ADDR,
port: ENDPOINT_STORAGE_DEFAULT_PORT,
},
pg_distrib_dir: None,
neon_distrib_dir: None,
@@ -1269,45 +1245,6 @@ async fn handle_timeline(cmd: &TimelineCmd, env: &mut local_env::LocalEnv) -> Re
pageserver
.timeline_import(tenant_id, timeline_id, base, pg_wal, args.pg_version)
.await?;
if env.storage_controller.timelines_onto_safekeepers {
println!("Creating timeline on safekeeper ...");
let timeline_info = pageserver
.timeline_info(
TenantShardId::unsharded(tenant_id),
timeline_id,
pageserver_client::mgmt_api::ForceAwaitLogicalSize::No,
)
.await?;
let default_sk = SafekeeperNode::from_env(env, env.safekeepers.first().unwrap());
let default_host = default_sk
.conf
.listen_addr
.clone()
.unwrap_or_else(|| "localhost".to_string());
let mconf = safekeeper_api::membership::Configuration {
generation: SafekeeperGeneration::new(1),
members: safekeeper_api::membership::MemberSet {
m: vec![SafekeeperId {
host: default_host,
id: default_sk.conf.id,
pg_port: default_sk.conf.pg_port,
}],
},
new_members: None,
};
let pg_version = PgVersionId::from(args.pg_version);
let req = safekeeper_api::models::TimelineCreateRequest {
tenant_id,
timeline_id,
mconf,
pg_version,
system_id: None,
wal_seg_size: None,
start_lsn: timeline_info.last_record_lsn,
commit_lsn: None,
};
default_sk.create_timeline(&req).await?;
}
env.register_branch_mapping(branch_name.to_string(), tenant_id, timeline_id)?;
println!("Done");
}
@@ -1332,7 +1269,6 @@ async fn handle_timeline(cmd: &TimelineCmd, env: &mut local_env::LocalEnv) -> Re
mode: pageserver_api::models::TimelineCreateRequestMode::Branch {
ancestor_timeline_id,
ancestor_start_lsn: start_lsn,
read_only: false,
pg_version: None,
},
};
@@ -1465,7 +1401,6 @@ async fn handle_endpoint(subcmd: &EndpointCmd, env: &local_env::LocalEnv) -> Res
args.internal_http_port,
args.pg_version,
mode,
args.grpc,
!args.update_catalog,
false,
)?;
@@ -1473,16 +1408,9 @@ async fn handle_endpoint(subcmd: &EndpointCmd, env: &local_env::LocalEnv) -> Res
EndpointCmd::Start(args) => {
let endpoint_id = &args.endpoint_id;
let pageserver_id = args.endpoint_pageserver_id;
let remote_ext_base_url = &args.remote_ext_base_url;
let remote_ext_config = &args.remote_ext_config;
let default_generation = env
.storage_controller
.timelines_onto_safekeepers
.then_some(1);
let safekeepers_generation = args
.safekeepers_generation
.or(default_generation)
.map(SafekeeperGeneration::new);
let safekeepers_generation = args.safekeepers_generation.map(SafekeeperGeneration::new);
// If --safekeepers argument is given, use only the listed
// safekeeper nodes; otherwise all from the env.
let safekeepers = if let Some(safekeepers) = parse_safekeepers(&args.safekeepers)? {
@@ -1506,20 +1434,13 @@ async fn handle_endpoint(subcmd: &EndpointCmd, env: &local_env::LocalEnv) -> Res
let (pageservers, stripe_size) = if let Some(pageserver_id) = pageserver_id {
let conf = env.get_pageserver_conf(pageserver_id).unwrap();
// Use gRPC if requested.
let pageserver = if endpoint.grpc {
let grpc_addr = conf.listen_grpc_addr.as_ref().expect("bad config");
let (host, port) = parse_host_port(grpc_addr)?;
let port = port.unwrap_or(DEFAULT_PAGESERVER_GRPC_PORT);
(PageserverProtocol::Grpc, host, port)
} else {
let (host, port) = parse_host_port(&conf.listen_pg_addr)?;
let port = port.unwrap_or(5432);
(PageserverProtocol::Libpq, host, port)
};
// If caller is telling us what pageserver to use, this is not a tenant which is
// fully managed by storage controller, therefore not sharded.
(vec![pageserver], DEFAULT_STRIPE_SIZE)
let parsed = parse_host_port(&conf.listen_pg_addr).expect("Bad config");
(
vec![(parsed.0, parsed.1.unwrap_or(5432))],
// If caller is telling us what pageserver to use, this is not a tenant which is
// full managed by storage controller, therefore not sharded.
DEFAULT_STRIPE_SIZE,
)
} else {
// Look up the currently attached location of the tenant, and its striping metadata,
// to pass these on to postgres.
@@ -1538,20 +1459,11 @@ async fn handle_endpoint(subcmd: &EndpointCmd, env: &local_env::LocalEnv) -> Res
.await?;
}
let pageserver = if endpoint.grpc {
(
PageserverProtocol::Grpc,
Host::parse(&shard.listen_grpc_addr.expect("no gRPC address"))?,
shard.listen_grpc_port.expect("no gRPC port"),
)
} else {
(
PageserverProtocol::Libpq,
Host::parse(&shard.listen_pg_addr)?,
shard.listen_pg_port,
)
};
anyhow::Ok(pageserver)
anyhow::Ok((
Host::parse(&shard.listen_pg_addr)
.expect("Storage controller reported bad hostname"),
shard.listen_pg_port,
))
}),
)
.await?;
@@ -1570,33 +1482,17 @@ async fn handle_endpoint(subcmd: &EndpointCmd, env: &local_env::LocalEnv) -> Res
None
};
let exp = (std::time::SystemTime::now().duration_since(std::time::UNIX_EPOCH)?
+ Duration::from_secs(86400))
.as_secs();
let claims = endpoint_storage::claims::EndpointStorageClaims {
tenant_id: endpoint.tenant_id,
timeline_id: endpoint.timeline_id,
endpoint_id: endpoint_id.to_string(),
exp,
};
let endpoint_storage_token = env.generate_auth_token(&claims)?;
let endpoint_storage_addr = env.endpoint_storage.listen_addr.to_string();
println!("Starting existing endpoint {endpoint_id}...");
endpoint
.start(
&auth_token,
endpoint_storage_token,
endpoint_storage_addr,
safekeepers_generation,
safekeepers,
pageservers,
remote_ext_base_url.as_ref(),
remote_ext_config.as_ref(),
stripe_size.0 as usize,
args.create_test_user,
args.start_timeout,
args.dev,
)
.await?;
}
@@ -1607,19 +1503,11 @@ async fn handle_endpoint(subcmd: &EndpointCmd, env: &local_env::LocalEnv) -> Res
.get(endpoint_id.as_str())
.with_context(|| format!("postgres endpoint {endpoint_id} is not found"))?;
let pageservers = if let Some(ps_id) = args.endpoint_pageserver_id {
let conf = env.get_pageserver_conf(ps_id)?;
// Use gRPC if requested.
let pageserver = if endpoint.grpc {
let grpc_addr = conf.listen_grpc_addr.as_ref().expect("bad config");
let (host, port) = parse_host_port(grpc_addr)?;
let port = port.unwrap_or(DEFAULT_PAGESERVER_GRPC_PORT);
(PageserverProtocol::Grpc, host, port)
} else {
let (host, port) = parse_host_port(&conf.listen_pg_addr)?;
let port = port.unwrap_or(5432);
(PageserverProtocol::Libpq, host, port)
};
vec![pageserver]
let pageserver = PageServerNode::from_env(env, env.get_pageserver_conf(ps_id)?);
vec![(
pageserver.pg_connection_config.host().clone(),
pageserver.pg_connection_config.port(),
)]
} else {
let storage_controller = StorageController::from_env(env);
storage_controller
@@ -1628,21 +1516,11 @@ async fn handle_endpoint(subcmd: &EndpointCmd, env: &local_env::LocalEnv) -> Res
.shards
.into_iter()
.map(|shard| {
// Use gRPC if requested.
if endpoint.grpc {
(
PageserverProtocol::Grpc,
Host::parse(&shard.listen_grpc_addr.expect("no gRPC address"))
.expect("bad hostname"),
shard.listen_grpc_port.expect("no gRPC port"),
)
} else {
(
PageserverProtocol::Libpq,
Host::parse(&shard.listen_pg_addr).expect("bad hostname"),
shard.listen_pg_port,
)
}
(
Host::parse(&shard.listen_pg_addr)
.expect("Storage controller reported malformed host"),
shard.listen_pg_port,
)
})
.collect::<Vec<_>>()
};
@@ -1657,22 +1535,15 @@ async fn handle_endpoint(subcmd: &EndpointCmd, env: &local_env::LocalEnv) -> Res
.endpoints
.get(endpoint_id)
.with_context(|| format!("postgres endpoint {endpoint_id} is not found"))?;
match endpoint.stop(args.mode, args.destroy).await?.lsn {
Some(lsn) => println!("{lsn}"),
None => println!("null"),
}
endpoint.stop(&args.mode, args.destroy)?;
}
EndpointCmd::GenerateJwt(args) => {
let endpoint = {
let endpoint_id = &args.endpoint_id;
cplane
.endpoints
.get(endpoint_id)
.with_context(|| format!("postgres endpoint {endpoint_id} is not found"))?
};
let jwt = endpoint.generate_jwt(args.scope)?;
let endpoint_id = &args.endpoint_id;
let endpoint = cplane
.endpoints
.get(endpoint_id)
.with_context(|| format!("postgres endpoint {endpoint_id} is not found"))?;
let jwt = endpoint.generate_jwt()?;
print!("{jwt}");
}
@@ -1742,7 +1613,7 @@ async fn handle_pageserver(subcmd: &PageserverCmd, env: &local_env::LocalEnv) ->
StopMode::Immediate => true,
};
if let Err(e) = get_pageserver(env, args.pageserver_id)?.stop(immediate) {
eprintln!("pageserver stop failed: {e}");
eprintln!("pageserver stop failed: {}", e);
exit(1);
}
}
@@ -1751,7 +1622,7 @@ async fn handle_pageserver(subcmd: &PageserverCmd, env: &local_env::LocalEnv) ->
let pageserver = get_pageserver(env, args.pageserver_id)?;
//TODO what shutdown strategy should we use here?
if let Err(e) = pageserver.stop(false) {
eprintln!("pageserver stop failed: {e}");
eprintln!("pageserver stop failed: {}", e);
exit(1);
}
@@ -1768,7 +1639,7 @@ async fn handle_pageserver(subcmd: &PageserverCmd, env: &local_env::LocalEnv) ->
{
Ok(_) => println!("Page server is up and running"),
Err(err) => {
eprintln!("Page server is not available: {err}");
eprintln!("Page server is not available: {}", err);
exit(1);
}
}
@@ -1805,7 +1676,7 @@ async fn handle_storage_controller(
},
};
if let Err(e) = svc.stop(stop_args).await {
eprintln!("stop failed: {e}");
eprintln!("stop failed: {}", e);
exit(1);
}
}
@@ -1827,7 +1698,7 @@ async fn handle_safekeeper(subcmd: &SafekeeperCmd, env: &local_env::LocalEnv) ->
let safekeeper = get_safekeeper(env, args.id)?;
if let Err(e) = safekeeper.start(&args.extra_opt, &args.start_timeout).await {
eprintln!("safekeeper start failed: {e}");
eprintln!("safekeeper start failed: {}", e);
exit(1);
}
}
@@ -1839,7 +1710,7 @@ async fn handle_safekeeper(subcmd: &SafekeeperCmd, env: &local_env::LocalEnv) ->
StopMode::Immediate => true,
};
if let Err(e) = safekeeper.stop(immediate) {
eprintln!("safekeeper stop failed: {e}");
eprintln!("safekeeper stop failed: {}", e);
exit(1);
}
}
@@ -1852,12 +1723,12 @@ async fn handle_safekeeper(subcmd: &SafekeeperCmd, env: &local_env::LocalEnv) ->
};
if let Err(e) = safekeeper.stop(immediate) {
eprintln!("safekeeper stop failed: {e}");
eprintln!("safekeeper stop failed: {}", e);
exit(1);
}
if let Err(e) = safekeeper.start(&args.extra_opt, &args.start_timeout).await {
eprintln!("safekeeper start failed: {e}");
eprintln!("safekeeper start failed: {}", e);
exit(1);
}
}
@@ -1906,8 +1777,7 @@ async fn handle_endpoint_storage(
async fn handle_storage_broker(subcmd: &StorageBrokerCmd, env: &local_env::LocalEnv) -> Result<()> {
match subcmd {
StorageBrokerCmd::Start(args) => {
let storage_broker = StorageBroker::from_env(env);
if let Err(e) = storage_broker.start(&args.start_timeout).await {
if let Err(e) = broker::start_broker_process(env, &args.start_timeout).await {
eprintln!("broker start failed: {e}");
exit(1);
}
@@ -1915,8 +1785,7 @@ async fn handle_storage_broker(subcmd: &StorageBrokerCmd, env: &local_env::Local
StorageBrokerCmd::Stop(_args) => {
// FIXME: stop_mode unused
let storage_broker = StorageBroker::from_env(env);
if let Err(e) = storage_broker.stop() {
if let Err(e) = broker::stop_broker_process(env) {
eprintln!("broker stop failed: {e}");
exit(1);
}
@@ -1966,11 +1835,8 @@ async fn handle_start_all_impl(
#[allow(clippy::redundant_closure_call)]
(|| {
js.spawn(async move {
let storage_broker = StorageBroker::from_env(env);
storage_broker
.start(&retry_timeout)
.await
.map_err(|e| e.context("start storage_broker"))
let retry_timeout = retry_timeout;
broker::start_broker_process(env, &retry_timeout).await
});
js.spawn(async move {
@@ -2092,16 +1958,11 @@ async fn handle_stop_all(args: &StopCmdArgs, env: &local_env::LocalEnv) -> Resul
}
async fn try_stop_all(env: &local_env::LocalEnv, immediate: bool) {
let mode = if immediate {
EndpointTerminateMode::Immediate
} else {
EndpointTerminateMode::Fast
};
// Stop all endpoints
match ComputeControlPlane::load(env.clone()) {
Ok(cplane) => {
for (_k, node) in cplane.endpoints {
if let Err(e) = node.stop(mode, false).await {
if let Err(e) = node.stop(if immediate { "immediate" } else { "fast" }, false) {
eprintln!("postgres stop failed: {e:#}");
}
}
@@ -2113,7 +1974,7 @@ async fn try_stop_all(env: &local_env::LocalEnv, immediate: bool) {
let storage = EndpointStorage::from_env(env);
if let Err(e) = storage.stop(immediate) {
eprintln!("endpoint_storage stop failed: {e:#}");
eprintln!("endpoint_storage stop failed: {:#}", e);
}
for ps_conf in &env.pageservers {
@@ -2130,8 +1991,7 @@ async fn try_stop_all(env: &local_env::LocalEnv, immediate: bool) {
}
}
let storage_broker = StorageBroker::from_env(env);
if let Err(e) = storage_broker.stop() {
if let Err(e) = broker::stop_broker_process(env) {
eprintln!("neon broker stop failed: {e:#}");
}

View File

@@ -3,86 +3,60 @@
//! In the local test environment, the storage broker stores its data directly in
//!
//! ```text
//! .neon/storage_broker
//! .neon
//! ```
use std::time::Duration;
use anyhow::Context;
use camino::Utf8PathBuf;
use crate::{background_process, local_env::LocalEnv};
use crate::{background_process, local_env};
pub struct StorageBroker {
env: LocalEnv,
pub async fn start_broker_process(
env: &local_env::LocalEnv,
retry_timeout: &Duration,
) -> anyhow::Result<()> {
let broker = &env.broker;
let listen_addr = &broker.listen_addr;
print!("Starting neon broker at {}", listen_addr);
let args = [format!("--listen-addr={listen_addr}")];
let client = reqwest::Client::new();
background_process::start_process(
"storage_broker",
&env.base_data_dir,
&env.storage_broker_bin(),
args,
[],
background_process::InitialPidFile::Create(storage_broker_pid_file_path(env)),
retry_timeout,
|| async {
let url = broker.client_url();
let status_url = url.join("status").with_context(|| {
format!("Failed to append /status path to broker endpoint {url}")
})?;
let request = client
.get(status_url)
.build()
.with_context(|| format!("Failed to construct request to broker endpoint {url}"))?;
match client.execute(request).await {
Ok(resp) => Ok(resp.status().is_success()),
Err(_) => Ok(false),
}
},
)
.await
.context("Failed to spawn storage_broker subprocess")?;
Ok(())
}
impl StorageBroker {
/// Create a new `StorageBroker` instance from the environment.
pub fn from_env(env: &LocalEnv) -> Self {
Self { env: env.clone() }
}
pub fn initialize(&self) -> anyhow::Result<()> {
if self.env.generate_local_ssl_certs {
self.env.generate_ssl_cert(
&self.env.storage_broker_data_dir().join("server.crt"),
&self.env.storage_broker_data_dir().join("server.key"),
)?;
}
Ok(())
}
/// Start the storage broker process.
pub async fn start(&self, retry_timeout: &Duration) -> anyhow::Result<()> {
let broker = &self.env.broker;
print!("Starting neon broker at {}", broker.client_url());
let mut args = Vec::new();
if let Some(addr) = &broker.listen_addr {
args.push(format!("--listen-addr={addr}"));
}
if let Some(addr) = &broker.listen_https_addr {
args.push(format!("--listen-https-addr={addr}"));
}
let client = self.env.create_http_client();
background_process::start_process(
"storage_broker",
&self.env.storage_broker_data_dir(),
&self.env.storage_broker_bin(),
args,
[],
background_process::InitialPidFile::Create(self.pid_file_path()),
retry_timeout,
|| async {
let url = broker.client_url();
let status_url = url.join("status").with_context(|| {
format!("Failed to append /status path to broker endpoint {url}")
})?;
let request = client.get(status_url).build().with_context(|| {
format!("Failed to construct request to broker endpoint {url}")
})?;
match client.execute(request).await {
Ok(resp) => Ok(resp.status().is_success()),
Err(_) => Ok(false),
}
},
)
.await
.context("Failed to spawn storage_broker subprocess")?;
Ok(())
}
/// Stop the storage broker process.
pub fn stop(&self) -> anyhow::Result<()> {
background_process::stop_process(true, "storage_broker", &self.pid_file_path())
}
/// Get the path to the PID file for the storage broker.
fn pid_file_path(&self) -> Utf8PathBuf {
Utf8PathBuf::from_path_buf(self.env.base_data_dir.join("storage_broker.pid"))
.expect("non-Unicode path")
}
pub fn stop_broker_process(env: &local_env::LocalEnv) -> anyhow::Result<()> {
background_process::stop_process(true, "storage_broker", &storage_broker_pid_file_path(env))
}
fn storage_broker_pid_file_path(env: &local_env::LocalEnv) -> Utf8PathBuf {
Utf8PathBuf::from_path_buf(env.base_data_dir.join("storage_broker.pid"))
.expect("non-Unicode path")
}

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