Compare commits

..

2 Commits

Author SHA1 Message Date
Bojan Serafimov
5edb0ccfa7 Add assertion 2023-01-24 15:23:27 -05:00
Bojan Serafimov
2bc1324bed Try im (benchmarks panic) 2023-01-24 14:36:22 -05:00
620 changed files with 28192 additions and 86068 deletions

View File

@@ -12,11 +12,5 @@ opt-level = 3
# Turn on a small amount of optimization in Development mode.
opt-level = 1
[build]
# This is only present for local builds, as it will be overridden
# by the RUSTDOCFLAGS env var in CI.
rustdocflags = ["-Arustdoc::private_intra_doc_links"]
[alias]
build_testing = ["build", "--features", "testing"]
neon = ["run", "--bin", "neon_local"]

View File

@@ -4,7 +4,7 @@
hakari-package = "workspace_hack"
# Format for `workspace-hack = ...` lines in other Cargo.tomls. Requires cargo-hakari 0.9.8 or above.
dep-format-version = "4"
dep-format-version = "3"
# Setting workspace.resolver = "2" in the root Cargo.toml is HIGHLY recommended.
# Hakari works much better with the new feature resolver.

View File

@@ -14,14 +14,9 @@
!pgxn/
!proxy/
!safekeeper/
!s3_scrubber/
!storage_broker/
!trace/
!vendor/postgres-v14/
!vendor/postgres-v15/
!vendor/postgres-v16/
!workspace_hack/
!neon_local/
!scripts/ninstall.sh
!scripts/combine_control_files.py
!vm-cgconfig.conf

View File

@@ -1,14 +1,10 @@
## Problem
## Describe your changes
## Summary of changes
## Issue ticket number and link
## Checklist before requesting a review
- [ ] I have performed a self-review of my code.
- [ ] If it is a core feature, I have added thorough tests.
- [ ] Do we need to implement analytics? if so did you add the relevant metrics to the dashboard?
- [ ] If this PR requires public announcement, mark it with /release-notes label and add several sentences in this section.
## Checklist before merging
- [ ] Do not forget to reformat commit message to not include the above checklist

View File

@@ -10,7 +10,6 @@
<!-- List everything that should be done **before** release, any issues / setting changes / etc -->
### Checklist after release
- [ ] Make sure instructions from PRs included in this release and labeled `manual_release_instructions` are executed (either by you or by people who wrote them).
- [ ] Based on the merged commits write release notes and open a PR into `website` repo ([example](https://github.com/neondatabase/website/pull/219/files))
- [ ] Check [#dev-production-stream](https://neondb.slack.com/archives/C03F5SM1N02) Slack channel
- [ ] Check [stuck projects page](https://console.neon.tech/admin/projects?sort=last_active&order=desc&stuck=true)

View File

@@ -1,8 +0,0 @@
self-hosted-runner:
labels:
- gen3
- large
- small
- us-east-2
config-variables:
- SLACK_UPCOMING_RELEASE_CHANNEL_ID

View File

@@ -1,241 +0,0 @@
name: 'Create Allure report'
description: 'Generate Allure report from uploaded by actions/allure-report-store tests results'
inputs:
store-test-results-into-db:
description: 'Whether to store test results into the database. TEST_RESULT_CONNSTR/TEST_RESULT_CONNSTR_NEW should be set'
type: boolean
required: false
default: false
outputs:
base-url:
description: 'Base URL for Allure report'
value: ${{ steps.generate-report.outputs.base-url }}
base-s3-url:
description: 'Base S3 URL for Allure report'
value: ${{ steps.generate-report.outputs.base-s3-url }}
report-url:
description: 'Allure report URL'
value: ${{ steps.generate-report.outputs.report-url }}
report-json-url:
description: 'Allure report JSON URL'
value: ${{ steps.generate-report.outputs.report-json-url }}
runs:
using: "composite"
steps:
# We're using some of env variables quite offen, so let's set them once.
#
# It would be nice to have them set in common runs.env[0] section, but it doesn't work[1]
#
# - [0] https://docs.github.com/en/actions/creating-actions/metadata-syntax-for-github-actions#runsenv
# - [1] https://github.com/neondatabase/neon/pull/3907#discussion_r1154703456
#
- name: Set variables
shell: bash -euxo pipefail {0}
run: |
PR_NUMBER=$(jq --raw-output .pull_request.number "$GITHUB_EVENT_PATH" || true)
if [ "${PR_NUMBER}" != "null" ]; then
BRANCH_OR_PR=pr-${PR_NUMBER}
elif [ "${GITHUB_REF_NAME}" = "main" ] || [ "${GITHUB_REF_NAME}" = "release" ]; then
# Shortcut for special branches
BRANCH_OR_PR=${GITHUB_REF_NAME}
else
BRANCH_OR_PR=branch-$(printf "${GITHUB_REF_NAME}" | tr -c "[:alnum:]._-" "-")
fi
LOCK_FILE=reports/${BRANCH_OR_PR}/lock.txt
WORKDIR=/tmp/${BRANCH_OR_PR}-$(date +%s)
mkdir -p ${WORKDIR}
echo "BRANCH_OR_PR=${BRANCH_OR_PR}" >> $GITHUB_ENV
echo "LOCK_FILE=${LOCK_FILE}" >> $GITHUB_ENV
echo "WORKDIR=${WORKDIR}" >> $GITHUB_ENV
echo "BUCKET=${BUCKET}" >> $GITHUB_ENV
env:
BUCKET: neon-github-public-dev
# TODO: We can replace with a special docker image with Java and Allure pre-installed
- uses: actions/setup-java@v3
with:
distribution: 'temurin'
java-version: '17'
- name: Install Allure
shell: bash -euxo pipefail {0}
run: |
if ! which allure; then
ALLURE_ZIP=allure-${ALLURE_VERSION}.zip
wget -q https://github.com/allure-framework/allure2/releases/download/${ALLURE_VERSION}/${ALLURE_ZIP}
echo "${ALLURE_ZIP_SHA256} ${ALLURE_ZIP}" | sha256sum --check
unzip -q ${ALLURE_ZIP}
echo "$(pwd)/allure-${ALLURE_VERSION}/bin" >> $GITHUB_PATH
rm -f ${ALLURE_ZIP}
fi
env:
ALLURE_VERSION: 2.23.1
ALLURE_ZIP_SHA256: 11141bfe727504b3fd80c0f9801eb317407fd0ac983ebb57e671f14bac4bcd86
# Potentially we could have several running build for the same key (for example, for the main branch), so we use improvised lock for this
- name: Acquire lock
shell: bash -euxo pipefail {0}
run: |
LOCK_TIMEOUT=300 # seconds
LOCK_CONTENT="${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}"
echo ${LOCK_CONTENT} > ${WORKDIR}/lock.txt
# Do it up to 5 times to avoid race condition
for _ in $(seq 1 5); do
for i in $(seq 1 ${LOCK_TIMEOUT}); do
LOCK_ACQUIRED=$(aws s3api head-object --bucket neon-github-public-dev --key ${LOCK_FILE} | jq --raw-output '.LastModified' || true)
# `date --date="..."` is supported only by gnu date (i.e. it doesn't work on BSD/macOS)
if [ -z "${LOCK_ACQUIRED}" ] || [ "$(( $(date +%s) - $(date --date="${LOCK_ACQUIRED}" +%s) ))" -gt "${LOCK_TIMEOUT}" ]; then
break
fi
sleep 1
done
aws s3 mv --only-show-errors ${WORKDIR}/lock.txt "s3://${BUCKET}/${LOCK_FILE}"
# Double-check that exactly THIS run has acquired the lock
aws s3 cp --only-show-errors "s3://${BUCKET}/${LOCK_FILE}" ./lock.txt
if [ "$(cat lock.txt)" = "${LOCK_CONTENT}" ]; then
break
fi
done
- name: Generate and publish final Allure report
id: generate-report
shell: bash -euxo pipefail {0}
run: |
REPORT_PREFIX=reports/${BRANCH_OR_PR}
RAW_PREFIX=reports-raw/${BRANCH_OR_PR}/${GITHUB_RUN_ID}
BASE_URL=https://${BUCKET}.s3.amazonaws.com/${REPORT_PREFIX}/${GITHUB_RUN_ID}
BASE_S3_URL=s3://${BUCKET}/${REPORT_PREFIX}/${GITHUB_RUN_ID}
REPORT_URL=${BASE_URL}/index.html
REPORT_JSON_URL=${BASE_URL}/data/suites.json
# Get previously uploaded data for this run
ZSTD_NBTHREADS=0
S3_FILEPATHS=$(aws s3api list-objects-v2 --bucket ${BUCKET} --prefix ${RAW_PREFIX}/ | jq --raw-output '.Contents[]?.Key')
if [ -z "$S3_FILEPATHS" ]; then
# There's no previously uploaded data for this $GITHUB_RUN_ID
exit 0
fi
time aws s3 cp --recursive --only-show-errors "s3://${BUCKET}/${RAW_PREFIX}/" "${WORKDIR}/"
for archive in $(find ${WORKDIR} -name "*.tar.zst"); do
mkdir -p ${archive%.tar.zst}
time tar -xf ${archive} -C ${archive%.tar.zst}
rm -f ${archive}
done
# Get history trend
time aws s3 cp --recursive --only-show-errors "s3://${BUCKET}/${REPORT_PREFIX}/latest/history" "${WORKDIR}/latest/history" || true
# Generate report
time allure generate --clean --output ${WORKDIR}/report ${WORKDIR}/*
# Replace a logo link with a redirect to the latest version of the report
sed -i 's|<a href="." class=|<a href="https://'${BUCKET}'.s3.amazonaws.com/'${REPORT_PREFIX}'/latest/index.html?nocache='"'+Date.now()+'"'" class=|g' ${WORKDIR}/report/app.js
# Upload a history and the final report (in this particular order to not to have duplicated history in 2 places)
time aws s3 mv --recursive --only-show-errors "${WORKDIR}/report/history" "s3://${BUCKET}/${REPORT_PREFIX}/latest/history"
# Use aws s3 cp (instead of aws s3 sync) to keep files from previous runs to make old URLs work,
# and to keep files on the host to upload them to the database
time aws s3 cp --recursive --only-show-errors "${WORKDIR}/report" "s3://${BUCKET}/${REPORT_PREFIX}/${GITHUB_RUN_ID}"
# Generate redirect
cat <<EOF > ${WORKDIR}/index.html
<!DOCTYPE html>
<meta charset="utf-8">
<title>Redirecting to ${REPORT_URL}</title>
<meta http-equiv="refresh" content="0; URL=${REPORT_URL}">
EOF
time aws s3 cp --only-show-errors ${WORKDIR}/index.html "s3://${BUCKET}/${REPORT_PREFIX}/latest/index.html"
echo "base-url=${BASE_URL}" >> $GITHUB_OUTPUT
echo "base-s3-url=${BASE_S3_URL}" >> $GITHUB_OUTPUT
echo "report-url=${REPORT_URL}" >> $GITHUB_OUTPUT
echo "report-json-url=${REPORT_JSON_URL}" >> $GITHUB_OUTPUT
echo "[Allure Report](${REPORT_URL})" >> ${GITHUB_STEP_SUMMARY}
- name: Release lock
if: always()
shell: bash -euxo pipefail {0}
run: |
aws s3 cp --only-show-errors "s3://${BUCKET}/${LOCK_FILE}" ./lock.txt || exit 0
if [ "$(cat lock.txt)" = "${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}" ]; then
aws s3 rm "s3://${BUCKET}/${LOCK_FILE}"
fi
- name: Store Allure test stat in the DB
if: ${{ !cancelled() && inputs.store-test-results-into-db == 'true' }}
shell: bash -euxo pipefail {0}
env:
COMMIT_SHA: ${{ github.event.pull_request.head.sha || github.sha }}
REPORT_JSON_URL: ${{ steps.generate-report.outputs.report-json-url }}
run: |
export DATABASE_URL=${REGRESS_TEST_RESULT_CONNSTR}
./scripts/pysync
poetry run python3 scripts/ingest_regress_test_result.py \
--revision ${COMMIT_SHA} \
--reference ${GITHUB_REF} \
--build-type unified \
--ingest ${WORKDIR}/report/data/suites.json
- name: Store Allure test stat in the DB (new)
if: ${{ !cancelled() && inputs.store-test-results-into-db == 'true' }}
shell: bash -euxo pipefail {0}
env:
COMMIT_SHA: ${{ github.event.pull_request.head.sha || github.sha }}
BASE_S3_URL: ${{ steps.generate-report.outputs.base-s3-url }}
run: |
export DATABASE_URL=${REGRESS_TEST_RESULT_CONNSTR_NEW}
./scripts/pysync
poetry run python3 scripts/ingest_regress_test_result-new-format.py \
--reference ${GITHUB_REF} \
--revision ${COMMIT_SHA} \
--run-id ${GITHUB_RUN_ID} \
--run-attempt ${GITHUB_RUN_ATTEMPT} \
--test-cases-dir ${WORKDIR}/report/data/test-cases
- name: Cleanup
if: always()
shell: bash -euxo pipefail {0}
run: |
if [ -d "${WORKDIR}" ]; then
rm -rf ${WORKDIR}
fi
- uses: actions/github-script@v6
if: always()
env:
REPORT_URL: ${{ steps.generate-report.outputs.report-url }}
COMMIT_SHA: ${{ github.event.pull_request.head.sha || github.sha }}
with:
script: |
const { REPORT_URL, COMMIT_SHA } = process.env
await github.rest.repos.createCommitStatus({
owner: context.repo.owner,
repo: context.repo.repo,
sha: `${COMMIT_SHA}`,
state: 'success',
target_url: `${REPORT_URL}`,
context: 'Allure report',
})

View File

@@ -1,72 +0,0 @@
name: 'Store Allure results'
description: 'Upload test results to be used by actions/allure-report-generate'
inputs:
report-dir:
description: 'directory with test results generated by tests'
required: true
unique-key:
description: 'string to distinguish different results in the same run'
required: true
runs:
using: "composite"
steps:
- name: Set variables
shell: bash -euxo pipefail {0}
run: |
PR_NUMBER=$(jq --raw-output .pull_request.number "$GITHUB_EVENT_PATH" || true)
if [ "${PR_NUMBER}" != "null" ]; then
BRANCH_OR_PR=pr-${PR_NUMBER}
elif [ "${GITHUB_REF_NAME}" = "main" ] || [ "${GITHUB_REF_NAME}" = "release" ]; then
# Shortcut for special branches
BRANCH_OR_PR=${GITHUB_REF_NAME}
else
BRANCH_OR_PR=branch-$(printf "${GITHUB_REF_NAME}" | tr -c "[:alnum:]._-" "-")
fi
echo "BRANCH_OR_PR=${BRANCH_OR_PR}" >> $GITHUB_ENV
echo "REPORT_DIR=${REPORT_DIR}" >> $GITHUB_ENV
env:
REPORT_DIR: ${{ inputs.report-dir }}
- name: Upload test results
shell: bash -euxo pipefail {0}
run: |
REPORT_PREFIX=reports/${BRANCH_OR_PR}
RAW_PREFIX=reports-raw/${BRANCH_OR_PR}/${GITHUB_RUN_ID}
# Add metadata
cat <<EOF > ${REPORT_DIR}/executor.json
{
"name": "GitHub Actions",
"type": "github",
"url": "https://${BUCKET}.s3.amazonaws.com/${REPORT_PREFIX}/latest/index.html",
"buildOrder": ${GITHUB_RUN_ID},
"buildName": "GitHub Actions Run #${GITHUB_RUN_NUMBER}/${GITHUB_RUN_ATTEMPT}",
"buildUrl": "${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}/attempts/${GITHUB_RUN_ATTEMPT}",
"reportUrl": "https://${BUCKET}.s3.amazonaws.com/${REPORT_PREFIX}/${GITHUB_RUN_ID}/index.html",
"reportName": "Allure Report"
}
EOF
cat <<EOF > ${REPORT_DIR}/environment.properties
COMMIT_SHA=${COMMIT_SHA}
EOF
ARCHIVE="${UNIQUE_KEY}-${GITHUB_RUN_ATTEMPT}-$(date +%s).tar.zst"
ZSTD_NBTHREADS=0
time tar -C ${REPORT_DIR} -cf ${ARCHIVE} --zstd .
time aws s3 mv --only-show-errors ${ARCHIVE} "s3://${BUCKET}/${RAW_PREFIX}/${ARCHIVE}"
env:
UNIQUE_KEY: ${{ inputs.unique-key }}
COMMIT_SHA: ${{ github.event.pull_request.head.sha || github.sha }}
BUCKET: neon-github-public-dev
- name: Cleanup
if: always()
shell: bash -euxo pipefail {0}
run: |
rm -rf ${REPORT_DIR}

232
.github/actions/allure-report/action.yml vendored Normal file
View File

@@ -0,0 +1,232 @@
name: 'Create Allure report'
description: 'Create and publish Allure report'
inputs:
action:
desctiption: 'generate or store'
required: true
build_type:
description: '`build_type` from run-python-test-set action'
required: true
test_selection:
description: '`test_selector` from run-python-test-set action'
required: false
outputs:
report-url:
description: 'Allure report URL'
value: ${{ steps.generate-report.outputs.report-url }}
runs:
using: "composite"
steps:
- name: Validate input parameters
shell: bash -euxo pipefail {0}
run: |
if [ "${{ inputs.action }}" != "store" ] && [ "${{ inputs.action }}" != "generate" ]; then
echo 2>&1 "Unknown inputs.action type '${{ inputs.action }}'; allowed 'generate' or 'store' only"
exit 1
fi
if [ -z "${{ inputs.test_selection }}" ] && [ "${{ inputs.action }}" == "store" ]; then
echo 2>&1 "inputs.test_selection must be set for 'store' action"
exit 2
fi
- name: Calculate variables
id: calculate-vars
shell: bash -euxo pipefail {0}
run: |
# TODO: for manually triggered workflows (via workflow_dispatch) we need to have a separate key
pr_number=$(jq --raw-output .pull_request.number "$GITHUB_EVENT_PATH" || true)
if [ "${pr_number}" != "null" ]; then
key=pr-${pr_number}
elif [ "${GITHUB_REF_NAME}" = "main" ]; then
# Shortcut for a special branch
key=main
elif [ "${GITHUB_REF_NAME}" = "release" ]; then
# Shortcut for a special branch
key=release
else
key=branch-$(printf "${GITHUB_REF_NAME}" | tr -c "[:alnum:]._-" "-")
fi
echo "KEY=${key}" >> $GITHUB_OUTPUT
# Sanitize test selection to remove `/` and any other special characters
# Use printf instead of echo to avoid having `\n` at the end of the string
test_selection=$(printf "${{ inputs.test_selection }}" | tr -c "[:alnum:]._-" "-" )
echo "TEST_SELECTION=${test_selection}" >> $GITHUB_OUTPUT
- uses: actions/setup-java@v3
if: ${{ inputs.action == 'generate' }}
with:
distribution: 'temurin'
java-version: '17'
- name: Install Allure
if: ${{ inputs.action == 'generate' }}
shell: bash -euxo pipefail {0}
run: |
if ! which allure; then
ALLURE_ZIP=allure-${ALLURE_VERSION}.zip
wget -q https://github.com/allure-framework/allure2/releases/download/${ALLURE_VERSION}/${ALLURE_ZIP}
echo "${ALLURE_ZIP_MD5} ${ALLURE_ZIP}" | md5sum -c
unzip -q ${ALLURE_ZIP}
echo "$(pwd)/allure-${ALLURE_VERSION}/bin" >> $GITHUB_PATH
rm -f ${ALLURE_ZIP}
fi
env:
ALLURE_VERSION: 2.19.0
ALLURE_ZIP_MD5: ced21401a1a8b9dfb68cee9e4c210464
- name: Upload Allure results
if: ${{ inputs.action == 'store' }}
env:
REPORT_PREFIX: reports/${{ steps.calculate-vars.outputs.KEY }}/${{ inputs.build_type }}
RAW_PREFIX: reports-raw/${{ steps.calculate-vars.outputs.KEY }}/${{ inputs.build_type }}
TEST_OUTPUT: /tmp/test_output
BUCKET: neon-github-public-dev
TEST_SELECTION: ${{ steps.calculate-vars.outputs.TEST_SELECTION }}
shell: bash -euxo pipefail {0}
run: |
# Add metadata
cat <<EOF > $TEST_OUTPUT/allure/results/executor.json
{
"name": "GitHub Actions",
"type": "github",
"url": "https://${BUCKET}.s3.amazonaws.com/${REPORT_PREFIX}/latest/index.html",
"buildOrder": ${GITHUB_RUN_ID},
"buildName": "GitHub Actions Run #${{ github.run_number }}/${GITHUB_RUN_ATTEMPT}",
"buildUrl": "${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}/attempts/${GITHUB_RUN_ATTEMPT}",
"reportUrl": "https://${BUCKET}.s3.amazonaws.com/${REPORT_PREFIX}/${GITHUB_RUN_ID}/index.html",
"reportName": "Allure Report"
}
EOF
cat <<EOF > $TEST_OUTPUT/allure/results/environment.properties
TEST_SELECTION=${{ inputs.test_selection }}
BUILD_TYPE=${{ inputs.build_type }}
EOF
ARCHIVE="${GITHUB_RUN_ID}-${TEST_SELECTION}-${GITHUB_RUN_ATTEMPT}-$(date +%s).tar.zst"
ZSTD_NBTHREADS=0
tar -C ${TEST_OUTPUT}/allure/results -cf ${ARCHIVE} --zstd .
aws s3 mv --only-show-errors ${ARCHIVE} "s3://${BUCKET}/${RAW_PREFIX}/${ARCHIVE}"
# Potentially we could have several running build for the same key (for example for the main branch), so we use improvised lock for this
- name: Acquire Allure lock
if: ${{ inputs.action == 'generate' }}
shell: bash -euxo pipefail {0}
env:
LOCK_FILE: reports/${{ steps.calculate-vars.outputs.KEY }}/lock.txt
BUCKET: neon-github-public-dev
TEST_SELECTION: ${{ steps.calculate-vars.outputs.TEST_SELECTION }}
run: |
LOCK_TIMEOUT=300 # seconds
for _ in $(seq 1 5); do
for i in $(seq 1 ${LOCK_TIMEOUT}); do
LOCK_ADDED=$(aws s3api head-object --bucket neon-github-public-dev --key ${LOCK_FILE} | jq --raw-output '.LastModified' || true)
# `date --date="..."` is supported only by gnu date (i.e. it doesn't work on BSD/macOS)
if [ -z "${LOCK_ADDED}" ] || [ "$(( $(date +%s) - $(date --date="${LOCK_ADDED}" +%s) ))" -gt "${LOCK_TIMEOUT}" ]; then
break
fi
sleep 1
done
echo "${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}-${TEST_SELECTION}" > lock.txt
aws s3 mv --only-show-errors lock.txt "s3://${BUCKET}/${LOCK_FILE}"
# A double-check that exactly WE have acquired the lock
aws s3 cp --only-show-errors "s3://${BUCKET}/${LOCK_FILE}" ./lock.txt
if [ "$(cat lock.txt)" = "${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}-${TEST_SELECTION}" ]; then
break
fi
done
- name: Generate and publish final Allure report
if: ${{ inputs.action == 'generate' }}
id: generate-report
env:
REPORT_PREFIX: reports/${{ steps.calculate-vars.outputs.KEY }}/${{ inputs.build_type }}
RAW_PREFIX: reports-raw/${{ steps.calculate-vars.outputs.KEY }}/${{ inputs.build_type }}
TEST_OUTPUT: /tmp/test_output
BUCKET: neon-github-public-dev
shell: bash -euxo pipefail {0}
run: |
# Get previously uploaded data for this run
ZSTD_NBTHREADS=0
s3_filepaths=$(aws s3api list-objects-v2 --bucket ${BUCKET} --prefix ${RAW_PREFIX}/${GITHUB_RUN_ID}- | jq --raw-output '.Contents[].Key')
if [ -z "$s3_filepaths" ]; then
# There's no previously uploaded data for this run
exit 0
fi
for s3_filepath in ${s3_filepaths}; do
aws s3 cp --only-show-errors "s3://${BUCKET}/${s3_filepath}" "${TEST_OUTPUT}/allure/"
archive=${TEST_OUTPUT}/allure/$(basename $s3_filepath)
mkdir -p ${archive%.tar.zst}
tar -xf ${archive} -C ${archive%.tar.zst}
rm -f ${archive}
done
# Get history trend
aws s3 cp --recursive --only-show-errors "s3://${BUCKET}/${REPORT_PREFIX}/latest/history" "${TEST_OUTPUT}/allure/latest/history" || true
# Generate report
allure generate --clean --output $TEST_OUTPUT/allure/report $TEST_OUTPUT/allure/*
# Replace a logo link with a redirect to the latest version of the report
sed -i 's|<a href="." class=|<a href="https://'${BUCKET}'.s3.amazonaws.com/'${REPORT_PREFIX}'/latest/index.html" class=|g' $TEST_OUTPUT/allure/report/app.js
# Upload a history and the final report (in this particular order to not to have duplicated history in 2 places)
aws s3 mv --recursive --only-show-errors "${TEST_OUTPUT}/allure/report/history" "s3://${BUCKET}/${REPORT_PREFIX}/latest/history"
aws s3 mv --recursive --only-show-errors "${TEST_OUTPUT}/allure/report" "s3://${BUCKET}/${REPORT_PREFIX}/${GITHUB_RUN_ID}"
REPORT_URL=https://${BUCKET}.s3.amazonaws.com/${REPORT_PREFIX}/${GITHUB_RUN_ID}/index.html
# Generate redirect
cat <<EOF > ./index.html
<!DOCTYPE html>
<meta charset="utf-8">
<title>Redirecting to ${REPORT_URL}</title>
<meta http-equiv="refresh" content="0; URL=${REPORT_URL}">
EOF
aws s3 cp --only-show-errors ./index.html "s3://${BUCKET}/${REPORT_PREFIX}/latest/index.html"
echo "[Allure Report](${REPORT_URL})" >> ${GITHUB_STEP_SUMMARY}
echo "report-url=${REPORT_URL}" >> $GITHUB_OUTPUT
- name: Release Allure lock
if: ${{ inputs.action == 'generate' && always() }}
shell: bash -euxo pipefail {0}
env:
LOCK_FILE: reports/${{ steps.calculate-vars.outputs.KEY }}/lock.txt
BUCKET: neon-github-public-dev
TEST_SELECTION: ${{ steps.calculate-vars.outputs.TEST_SELECTION }}
run: |
aws s3 cp --only-show-errors "s3://${BUCKET}/${LOCK_FILE}" ./lock.txt || exit 0
if [ "$(cat lock.txt)" = "${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}-${TEST_SELECTION}" ]; then
aws s3 rm "s3://${BUCKET}/${LOCK_FILE}"
fi
- uses: actions/github-script@v6
if: ${{ inputs.action == 'generate' && always() }}
env:
REPORT_URL: ${{ steps.generate-report.outputs.report-url }}
BUILD_TYPE: ${{ inputs.build_type }}
SHA: ${{ github.event.pull_request.head.sha || github.sha }}
with:
script: |
const { REPORT_URL, BUILD_TYPE, SHA } = process.env
await github.rest.repos.createCommitStatus({
owner: context.repo.owner,
repo: context.repo.repo,
sha: `${SHA}`,
state: 'success',
target_url: `${REPORT_URL}`,
context: `Allure report / ${BUILD_TYPE}`,
})

View File

@@ -31,13 +31,13 @@ runs:
BUCKET=neon-github-public-dev
FILENAME=$(basename $ARCHIVE)
S3_KEY=$(aws s3api list-objects-v2 --bucket ${BUCKET} --prefix ${PREFIX%$GITHUB_RUN_ATTEMPT} | jq -r '.Contents[]?.Key' | grep ${FILENAME} | sort --version-sort | tail -1 || true)
S3_KEY=$(aws s3api list-objects-v2 --bucket ${BUCKET} --prefix ${PREFIX%$GITHUB_RUN_ATTEMPT} | jq -r '.Contents[].Key' | grep ${FILENAME} | sort --version-sort | tail -1 || true)
if [ -z "${S3_KEY}" ]; then
if [ "${SKIP_IF_DOES_NOT_EXIST}" = "true" ]; then
echo 'SKIPPED=true' >> $GITHUB_OUTPUT
exit 0
else
echo >&2 "Neither s3://${BUCKET}/${PREFIX}/${FILENAME} nor its version from previous attempts exist"
echo 2>&1 "Neither s3://${BUCKET}/${PREFIX}/${FILENAME} nor its version from previous attempts exist"
exit 1
fi
fi

View File

@@ -58,7 +58,7 @@ runs:
done
if [ -z "${branch_id}" ] || [ "${branch_id}" == "null" ]; then
echo >&2 "Failed to create branch after 10 attempts, the latest response was: ${branch}"
echo 2>&1 "Failed to create branch after 10 attempts, the latest response was: ${branch}"
exit 1
fi
@@ -122,7 +122,7 @@ runs:
done
if [ -z "${password}" ] || [ "${password}" == "null" ]; then
echo >&2 "Failed to reset password after 10 attempts, the latest response was: ${reset_password}"
echo 2>&1 "Failed to reset password after 10 attempts, the latest response was: ${reset_password}"
exit 1
fi

View File

@@ -48,7 +48,7 @@ runs:
done
if [ -z "${branch_id}" ] || [ "${branch_id}" == "null" ]; then
echo >&2 "Failed to delete branch after 10 attempts, the latest response was: ${deleted_branch}"
echo 2>&1 "Failed to delete branch after 10 attempts, the latest response was: ${deleted_branch}"
exit 1
fi
env:

View File

@@ -14,12 +14,6 @@ inputs:
api_host:
desctiption: 'Neon API host'
default: console.stage.neon.tech
provisioner:
desctiption: 'k8s-pod or k8s-neonvm'
default: 'k8s-pod'
compute_units:
desctiption: '[Min, Max] compute units; Min and Max are used for k8s-neonvm with autoscaling, for k8s-pod values Min and Max should be equal'
default: '[1, 1]'
outputs:
dsn:
@@ -37,10 +31,6 @@ runs:
# A shell without `set -x` to not to expose password/dsn in logs
shell: bash -euo pipefail {0}
run: |
if [ "${PROVISIONER}" == "k8s-pod" ] && [ "${MIN_CU}" != "${MAX_CU}" ]; then
echo >&2 "For k8s-pod provisioner MIN_CU should be equal to MAX_CU"
fi
project=$(curl \
"https://${API_HOST}/api/v2/projects" \
--fail \
@@ -52,9 +42,6 @@ runs:
\"name\": \"Created by actions/neon-project-create; GITHUB_RUN_ID=${GITHUB_RUN_ID}\",
\"pg_version\": ${POSTGRES_VERSION},
\"region_id\": \"${REGION_ID}\",
\"provisioner\": \"${PROVISIONER}\",
\"autoscaling_limit_min_cu\": ${MIN_CU},
\"autoscaling_limit_max_cu\": ${MAX_CU},
\"settings\": { }
}
}")
@@ -75,6 +62,3 @@ runs:
API_KEY: ${{ inputs.api_key }}
REGION_ID: ${{ inputs.region_id }}
POSTGRES_VERSION: ${{ inputs.postgres_version }}
PROVISIONER: ${{ inputs.provisioner }}
MIN_CU: ${{ fromJSON(inputs.compute_units)[0] }}
MAX_CU: ${{ fromJSON(inputs.compute_units)[1] }}

View File

@@ -36,14 +36,14 @@ inputs:
description: 'Region name for real s3 tests'
required: false
default: ''
rerun_flaky:
description: 'Whether to rerun flaky tests'
real_s3_access_key_id:
description: 'Access key id'
required: false
default: 'false'
pg_version:
description: 'Postgres version to use for tests'
default: ''
real_s3_secret_access_key:
description: 'Secret access key'
required: false
default: 'v14'
default: ''
runs:
using: "composite"
@@ -63,16 +63,13 @@ runs:
path: /tmp/neon-previous
prefix: latest
- name: Download compatibility snapshot
- name: Download compatibility snapshot for Postgres 14
if: inputs.build_type != 'remote'
uses: ./.github/actions/download
with:
name: compatibility-snapshot-${{ inputs.build_type }}-pg${{ inputs.pg_version }}
path: /tmp/compatibility_snapshot_pg${{ inputs.pg_version }}
name: compatibility-snapshot-${{ inputs.build_type }}-pg14
path: /tmp/compatibility_snapshot_pg14
prefix: latest
# 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
- name: Checkout
if: inputs.needs_postgres_source == 'true'
@@ -99,18 +96,18 @@ runs:
COMPATIBILITY_POSTGRES_DISTRIB_DIR: /tmp/neon-previous/pg_install
TEST_OUTPUT: /tmp/test_output
BUILD_TYPE: ${{ inputs.build_type }}
COMPATIBILITY_SNAPSHOT_DIR: /tmp/compatibility_snapshot_pg${{ inputs.pg_version }}
AWS_ACCESS_KEY_ID: ${{ inputs.real_s3_access_key_id }}
AWS_SECRET_ACCESS_KEY: ${{ inputs.real_s3_secret_access_key }}
COMPATIBILITY_SNAPSHOT_DIR: /tmp/compatibility_snapshot_pg14
ALLOW_BACKWARD_COMPATIBILITY_BREAKAGE: contains(github.event.pull_request.labels.*.name, 'backward compatibility breakage')
ALLOW_FORWARD_COMPATIBILITY_BREAKAGE: contains(github.event.pull_request.labels.*.name, 'forward compatibility breakage')
RERUN_FLAKY: ${{ inputs.rerun_flaky }}
PG_VERSION: ${{ inputs.pg_version }}
shell: bash -euxo pipefail {0}
run: |
# PLATFORM will be embedded in the perf test report
# and it is needed to distinguish different environments
export PLATFORM=${PLATFORM:-github-actions-selfhosted}
export POSTGRES_DISTRIB_DIR=${POSTGRES_DISTRIB_DIR:-/tmp/neon/pg_install}
export DEFAULT_PG_VERSION=${PG_VERSION#v}
export DEFAULT_PG_VERSION=${DEFAULT_PG_VERSION:-14}
if [ "${BUILD_TYPE}" = "remote" ]; then
export REMOTE_ENV=1
@@ -126,8 +123,8 @@ runs:
exit 1
fi
if [[ "${{ inputs.run_in_parallel }}" == "true" ]]; then
# -n16 uses sixteen processes to run tests via pytest-xdist
EXTRA_PARAMS="-n16 $EXTRA_PARAMS"
# -n4 uses four processes to run tests via pytest-xdist
EXTRA_PARAMS="-n4 $EXTRA_PARAMS"
# --dist=loadgroup points tests marked with @pytest.mark.xdist_group
# to the same worker to make @pytest.mark.order work with xdist
@@ -146,25 +143,6 @@ runs:
EXTRA_PARAMS="--out-dir $PERF_REPORT_DIR $EXTRA_PARAMS"
fi
if [ "${RERUN_FLAKY}" == "true" ]; then
mkdir -p $TEST_OUTPUT
poetry run ./scripts/flaky_tests.py "${TEST_RESULT_CONNSTR}" \
--days 7 \
--output "$TEST_OUTPUT/flaky.json" \
--pg-version "${DEFAULT_PG_VERSION}" \
--build-type "${BUILD_TYPE}"
EXTRA_PARAMS="--flaky-tests-json $TEST_OUTPUT/flaky.json $EXTRA_PARAMS"
fi
# We use pytest-split plugin to run benchmarks in parallel on different CI runners
if [ "${TEST_SELECTION}" = "test_runner/performance" ] && [ "${{ inputs.build_type }}" != "remote" ]; then
mkdir -p $TEST_OUTPUT
poetry run ./scripts/benchmark_durations.py "${TEST_RESULT_CONNSTR}" --days 10 --output "$TEST_OUTPUT/benchmark_durations.json"
EXTRA_PARAMS="--durations-path $TEST_OUTPUT/benchmark_durations.json $EXTRA_PARAMS"
fi
if [[ "${{ inputs.build_type }}" == "debug" ]]; then
cov_prefix=(scripts/coverage "--profraw-prefix=$GITHUB_JOB" --dir=/tmp/coverage run)
elif [[ "${{ inputs.build_type }}" == "release" ]]; then
@@ -202,18 +180,19 @@ runs:
scripts/generate_and_push_perf_report.sh
fi
- name: Upload compatibility snapshot
- name: Upload compatibility snapshot for Postgres 14
if: github.ref_name == 'release'
uses: ./.github/actions/upload
with:
name: compatibility-snapshot-${{ inputs.build_type }}-pg${{ inputs.pg_version }}-${{ github.run_id }}
# Directory is created by test_compatibility.py::test_create_snapshot, keep the path in sync with the test
path: /tmp/test_output/compatibility_snapshot_pg${{ inputs.pg_version }}/
name: compatibility-snapshot-${{ inputs.build_type }}-pg14-${{ github.run_id }}
# The path includes a test name (test_create_snapshot) and directory that the test creates (compatibility_snapshot_pg14), keep the path in sync with the test
path: /tmp/test_output/test_create_snapshot/compatibility_snapshot_pg14/
prefix: latest
- name: Upload test results
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-store
- name: Create Allure report
if: success() || failure()
uses: ./.github/actions/allure-report
with:
report-dir: /tmp/test_output/allure/results
unique-key: ${{ inputs.build_type }}-${{ inputs.pg_version }}
action: store
build_type: ${{ inputs.build_type }}
test_selection: ${{ inputs.test_selection }}

View File

@@ -23,7 +23,7 @@ runs:
mkdir -p $(dirname $ARCHIVE)
if [ -f ${ARCHIVE} ]; then
echo >&2 "File ${ARCHIVE} already exist. Something went wrong before"
echo 2>&1 "File ${ARCHIVE} already exist. Something went wrong before"
exit 1
fi
@@ -33,10 +33,10 @@ runs:
elif [ -f ${SOURCE} ]; then
time tar -cf ${ARCHIVE} --zstd ${SOURCE}
elif ! ls ${SOURCE} > /dev/null 2>&1; then
echo >&2 "${SOURCE} does not exist"
echo 2>&1 "${SOURCE} does not exist"
exit 2
else
echo >&2 "${SOURCE} is neither a directory nor a file, do not know how to handle it"
echo 2>&1 "${SOURCE} is neither a directory nor a file, do not know how to handle it"
exit 3
fi

5
.github/ansible/.gitignore vendored Normal file
View File

@@ -0,0 +1,5 @@
neon_install.tar.gz
.neon_current_version
collections/*
!collections/.keep

12
.github/ansible/ansible.cfg vendored Normal file
View File

@@ -0,0 +1,12 @@
[defaults]
localhost_warning = False
host_key_checking = False
timeout = 30
[ssh_connection]
ssh_args = -F ./ansible.ssh.cfg
# teleport doesn't support sftp yet https://github.com/gravitational/teleport/issues/7127
# and scp neither worked for me
transfer_method = piped
pipelining = True

15
.github/ansible/ansible.ssh.cfg vendored Normal file
View File

@@ -0,0 +1,15 @@
# Remove this once https://github.com/gravitational/teleport/issues/10918 is fixed
# (use pre 8.5 option name to cope with old ssh in CI)
PubkeyAcceptedKeyTypes +ssh-rsa-cert-v01@openssh.com
Host tele.zenith.tech
User admin
Port 3023
StrictHostKeyChecking no
UserKnownHostsFile /dev/null
Host * !tele.zenith.tech
User admin
StrictHostKeyChecking no
UserKnownHostsFile /dev/null
ProxyJump tele.zenith.tech

193
.github/ansible/deploy.yaml vendored Normal file
View File

@@ -0,0 +1,193 @@
- name: Upload Neon binaries
hosts: storage
gather_facts: False
remote_user: "{{ remote_user }}"
tasks:
- name: get latest version of Neon binaries
register: current_version_file
set_fact:
current_version: "{{ lookup('file', '.neon_current_version') | trim }}"
tags:
- pageserver
- safekeeper
- name: inform about versions
debug:
msg: "Version to deploy - {{ current_version }}"
tags:
- pageserver
- safekeeper
- name: upload and extract Neon binaries to /usr/local
ansible.builtin.unarchive:
owner: root
group: root
src: neon_install.tar.gz
dest: /usr/local
become: true
tags:
- pageserver
- safekeeper
- binaries
- putbinaries
- name: Deploy pageserver
hosts: pageservers
gather_facts: False
remote_user: "{{ remote_user }}"
tasks:
- name: upload init script
when: console_mgmt_base_url is defined
ansible.builtin.template:
src: scripts/init_pageserver.sh
dest: /tmp/init_pageserver.sh
owner: root
group: root
mode: '0755'
become: true
tags:
- pageserver
- name: init pageserver
shell:
cmd: /tmp/init_pageserver.sh
args:
creates: "/storage/pageserver/data/tenants"
environment:
NEON_REPO_DIR: "/storage/pageserver/data"
LD_LIBRARY_PATH: "/usr/local/v14/lib"
become: true
tags:
- pageserver
- name: read the existing remote pageserver config
ansible.builtin.slurp:
src: /storage/pageserver/data/pageserver.toml
register: _remote_ps_config
tags:
- pageserver
- name: parse the existing pageserver configuration
ansible.builtin.set_fact:
_existing_ps_config: "{{ _remote_ps_config['content'] | b64decode | sivel.toiletwater.from_toml }}"
tags:
- pageserver
- name: construct the final pageserver configuration dict
ansible.builtin.set_fact:
pageserver_config: "{{ pageserver_config_stub | combine({'id': _existing_ps_config.id }) }}"
tags:
- pageserver
- name: template the pageserver config
template:
src: templates/pageserver.toml.j2
dest: /storage/pageserver/data/pageserver.toml
become: true
tags:
- pageserver
- name: upload systemd service definition
ansible.builtin.template:
src: systemd/pageserver.service
dest: /etc/systemd/system/pageserver.service
owner: root
group: root
mode: '0644'
become: true
tags:
- pageserver
- name: start systemd service
ansible.builtin.systemd:
daemon_reload: yes
name: pageserver
enabled: yes
state: restarted
become: true
tags:
- pageserver
- name: post version to console
when: console_mgmt_base_url is defined
shell:
cmd: |
INSTANCE_ID=$(curl -s http://169.254.169.254/latest/meta-data/instance-id)
curl -sfS -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" {{ console_mgmt_base_url }}/management/api/v2/pageservers/$INSTANCE_ID | jq '.version = {{ current_version }}' > /tmp/new_version
curl -sfS -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" -X POST -d@/tmp/new_version {{ console_mgmt_base_url }}/management/api/v2/pageservers
tags:
- pageserver
- name: Deploy safekeeper
hosts: safekeepers
gather_facts: False
remote_user: "{{ remote_user }}"
tasks:
- name: upload init script
when: console_mgmt_base_url is defined
ansible.builtin.template:
src: scripts/init_safekeeper.sh
dest: /tmp/init_safekeeper.sh
owner: root
group: root
mode: '0755'
become: true
tags:
- safekeeper
- name: init safekeeper
shell:
cmd: /tmp/init_safekeeper.sh
args:
creates: "/storage/safekeeper/data/safekeeper.id"
environment:
NEON_REPO_DIR: "/storage/safekeeper/data"
LD_LIBRARY_PATH: "/usr/local/v14/lib"
become: true
tags:
- safekeeper
# in the future safekeepers should discover pageservers byself
# but currently use first pageserver that was discovered
- name: set first pageserver var for safekeepers
set_fact:
first_pageserver: "{{ hostvars[groups['pageservers'][0]]['inventory_hostname'] }}"
tags:
- safekeeper
- name: upload systemd service definition
ansible.builtin.template:
src: systemd/safekeeper.service
dest: /etc/systemd/system/safekeeper.service
owner: root
group: root
mode: '0644'
become: true
tags:
- safekeeper
- name: start systemd service
ansible.builtin.systemd:
daemon_reload: yes
name: safekeeper
enabled: yes
state: restarted
become: true
tags:
- safekeeper
- name: post version to console
when: console_mgmt_base_url is defined
shell:
cmd: |
INSTANCE_ID=$(curl -s http://169.254.169.254/latest/meta-data/instance-id)
curl -sfS -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" {{ console_mgmt_base_url }}/management/api/v2/safekeepers/$INSTANCE_ID | jq '.version = {{ current_version }}' > /tmp/new_version
curl -sfS -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" -X POST -d@/tmp/new_version {{ console_mgmt_base_url }}/management/api/v2/safekeepers
tags:
- safekeeper

42
.github/ansible/get_binaries.sh vendored Executable file
View File

@@ -0,0 +1,42 @@
#!/bin/bash
set -e
if [ -n "${DOCKER_TAG}" ]; then
# Verson is DOCKER_TAG but without prefix
VERSION=$(echo $DOCKER_TAG | sed 's/^.*-//g')
else
echo "Please set DOCKER_TAG environment variable"
exit 1
fi
# do initial cleanup
rm -rf neon_install postgres_install.tar.gz neon_install.tar.gz .neon_current_version
mkdir neon_install
# retrieve binaries from docker image
echo "getting binaries from docker image"
docker pull --quiet neondatabase/neon:${DOCKER_TAG}
ID=$(docker create neondatabase/neon:${DOCKER_TAG})
docker cp ${ID}:/data/postgres_install.tar.gz .
tar -xzf postgres_install.tar.gz -C neon_install
mkdir neon_install/bin/
docker cp ${ID}:/usr/local/bin/pageserver neon_install/bin/
docker cp ${ID}:/usr/local/bin/pageserver_binutils neon_install/bin/
docker cp ${ID}:/usr/local/bin/safekeeper neon_install/bin/
docker cp ${ID}:/usr/local/bin/storage_broker neon_install/bin/
docker cp ${ID}:/usr/local/bin/proxy neon_install/bin/
docker cp ${ID}:/usr/local/v14/bin/ neon_install/v14/bin/
docker cp ${ID}:/usr/local/v15/bin/ neon_install/v15/bin/
docker cp ${ID}:/usr/local/v14/lib/ neon_install/v14/lib/
docker cp ${ID}:/usr/local/v15/lib/ neon_install/v15/lib/
docker rm -vf ${ID}
# store version to file (for ansible playbooks) and create binaries tarball
echo ${VERSION} > neon_install/.neon_current_version
echo ${VERSION} > .neon_current_version
tar -czf neon_install.tar.gz -C neon_install .
# do final cleaup
rm -rf neon_install postgres_install.tar.gz

View File

@@ -0,0 +1,38 @@
storage:
vars:
bucket_name: neon-prod-storage-ap-southeast-1
bucket_region: ap-southeast-1
console_mgmt_base_url: http://console-release.local
broker_endpoint: http://storage-broker-lb.epsilon.ap-southeast-1.internal.aws.neon.tech:50051
pageserver_config_stub:
pg_distrib_dir: /usr/local
metric_collection_endpoint: http://console-release.local/billing/api/v1/usage_events
metric_collection_interval: 10min
remote_storage:
bucket_name: "{{ bucket_name }}"
bucket_region: "{{ bucket_region }}"
prefix_in_bucket: "pageserver/v1"
safekeeper_s3_prefix: safekeeper/v1/wal
hostname_suffix: ""
remote_user: ssm-user
ansible_aws_ssm_region: ap-southeast-1
ansible_aws_ssm_bucket_name: neon-prod-storage-ap-southeast-1
console_region_id: aws-ap-southeast-1
sentry_environment: production
children:
pageservers:
hosts:
pageserver-0.ap-southeast-1.aws.neon.tech:
ansible_host: i-064de8ea28bdb495b
pageserver-1.ap-southeast-1.aws.neon.tech:
ansible_host: i-0b180defcaeeb6b93
safekeepers:
hosts:
safekeeper-0.ap-southeast-1.aws.neon.tech:
ansible_host: i-0d6f1dc5161eef894
safekeeper-1.ap-southeast-1.aws.neon.tech:
ansible_host: i-0e338adda8eb2d19f
safekeeper-2.ap-southeast-1.aws.neon.tech:
ansible_host: i-04fb63634e4679eb9

View File

@@ -0,0 +1,38 @@
storage:
vars:
bucket_name: neon-prod-storage-eu-central-1
bucket_region: eu-central-1
console_mgmt_base_url: http://console-release.local
broker_endpoint: http://storage-broker-lb.gamma.eu-central-1.internal.aws.neon.tech:50051
pageserver_config_stub:
pg_distrib_dir: /usr/local
metric_collection_endpoint: http://console-release.local/billing/api/v1/usage_events
metric_collection_interval: 10min
remote_storage:
bucket_name: "{{ bucket_name }}"
bucket_region: "{{ bucket_region }}"
prefix_in_bucket: "pageserver/v1"
safekeeper_s3_prefix: safekeeper/v1/wal
hostname_suffix: ""
remote_user: ssm-user
ansible_aws_ssm_region: eu-central-1
ansible_aws_ssm_bucket_name: neon-prod-storage-eu-central-1
console_region_id: aws-eu-central-1
sentry_environment: production
children:
pageservers:
hosts:
pageserver-0.eu-central-1.aws.neon.tech:
ansible_host: i-0cd8d316ecbb715be
pageserver-1.eu-central-1.aws.neon.tech:
ansible_host: i-090044ed3d383fef0
safekeepers:
hosts:
safekeeper-0.eu-central-1.aws.neon.tech:
ansible_host: i-0b238612d2318a050
safekeeper-1.eu-central-1.aws.neon.tech:
ansible_host: i-07b9c45e5c2637cd4
safekeeper-2.eu-central-1.aws.neon.tech:
ansible_host: i-020257302c3c93d88

View File

@@ -0,0 +1,39 @@
storage:
vars:
bucket_name: neon-prod-storage-us-east-2
bucket_region: us-east-2
console_mgmt_base_url: http://console-release.local
broker_endpoint: http://storage-broker-lb.delta.us-east-2.internal.aws.neon.tech:50051
pageserver_config_stub:
pg_distrib_dir: /usr/local
metric_collection_endpoint: http://console-release.local/billing/api/v1/usage_events
metric_collection_interval: 10min
remote_storage:
bucket_name: "{{ bucket_name }}"
bucket_region: "{{ bucket_region }}"
prefix_in_bucket: "pageserver/v1"
safekeeper_s3_prefix: safekeeper/v1/wal
hostname_suffix: ""
remote_user: ssm-user
ansible_aws_ssm_region: us-east-2
ansible_aws_ssm_bucket_name: neon-prod-storage-us-east-2
console_region_id: aws-us-east-2
sentry_environment: production
children:
pageservers:
hosts:
pageserver-0.us-east-2.aws.neon.tech:
ansible_host: i-062227ba7f119eb8c
pageserver-1.us-east-2.aws.neon.tech:
ansible_host: i-0b3ec0afab5968938
safekeepers:
hosts:
safekeeper-0.us-east-2.aws.neon.tech:
ansible_host: i-0e94224750c57d346
safekeeper-1.us-east-2.aws.neon.tech:
ansible_host: i-06d113fb73bfddeb0
safekeeper-2.us-east-2.aws.neon.tech:
ansible_host: i-09f66c8e04afff2e8

View File

@@ -0,0 +1,41 @@
storage:
vars:
bucket_name: neon-prod-storage-us-west-2
bucket_region: us-west-2
console_mgmt_base_url: http://console-release.local
broker_endpoint: http://storage-broker-lb.eta.us-west-2.internal.aws.neon.tech:50051
pageserver_config_stub:
pg_distrib_dir: /usr/local
metric_collection_endpoint: http://console-release.local/billing/api/v1/usage_events
metric_collection_interval: 10min
remote_storage:
bucket_name: "{{ bucket_name }}"
bucket_region: "{{ bucket_region }}"
prefix_in_bucket: "pageserver/v1"
safekeeper_s3_prefix: safekeeper/v1/wal
hostname_suffix: ""
remote_user: ssm-user
ansible_aws_ssm_region: us-west-2
ansible_aws_ssm_bucket_name: neon-prod-storage-us-west-2
console_region_id: aws-us-west-2-new
sentry_environment: production
children:
pageservers:
hosts:
pageserver-0.us-west-2.aws.neon.tech:
ansible_host: i-0d9f6dfae0e1c780d
pageserver-1.us-west-2.aws.neon.tech:
ansible_host: i-0c834be1dddba8b3f
pageserver-2.us-west-2.aws.neon.tech:
ansible_host: i-051642d372c0a4f32
safekeepers:
hosts:
safekeeper-0.us-west-2.aws.neon.tech:
ansible_host: i-00719d8a74986fda6
safekeeper-1.us-west-2.aws.neon.tech:
ansible_host: i-074682f9d3c712e7c
safekeeper-2.us-west-2.aws.neon.tech:
ansible_host: i-042b7efb1729d7966

40
.github/ansible/production.hosts.yaml vendored Normal file
View File

@@ -0,0 +1,40 @@
---
storage:
vars:
console_mgmt_base_url: http://console-release.local
bucket_name: zenith-storage-oregon
bucket_region: us-west-2
broker_endpoint: http://storage-broker.prod.local:50051
pageserver_config_stub:
pg_distrib_dir: /usr/local
metric_collection_endpoint: http://console-release.local/billing/api/v1/usage_events
metric_collection_interval: 10min
remote_storage:
bucket_name: "{{ bucket_name }}"
bucket_region: "{{ bucket_region }}"
prefix_in_bucket: "{{ inventory_hostname }}"
safekeeper_s3_prefix: prod-1/wal
hostname_suffix: ".local"
remote_user: admin
sentry_environment: production
children:
pageservers:
hosts:
zenith-1-ps-2:
console_region_id: aws-us-west-2
zenith-1-ps-3:
console_region_id: aws-us-west-2
zenith-1-ps-4:
console_region_id: aws-us-west-2
zenith-1-ps-5:
console_region_id: aws-us-west-2
safekeepers:
hosts:
zenith-1-sk-1:
console_region_id: aws-us-west-2
zenith-1-sk-2:
console_region_id: aws-us-west-2
zenith-1-sk-4:
console_region_id: aws-us-west-2

View File

@@ -0,0 +1,33 @@
#!/bin/sh
# fetch params from meta-data service
INSTANCE_ID=$(curl -s http://169.254.169.254/latest/meta-data/instance-id)
AZ_ID=$(curl -s http://169.254.169.254/latest/meta-data/placement/availability-zone)
# store fqdn hostname in var
HOST=$(hostname -f)
cat <<EOF | tee /tmp/payload
{
"version": 1,
"host": "${HOST}",
"port": 6400,
"region_id": "{{ console_region_id }}",
"instance_id": "${INSTANCE_ID}",
"http_host": "${HOST}",
"http_port": 9898,
"active": false,
"availability_zone_id": "${AZ_ID}"
}
EOF
# check if pageserver already registered or not
if ! curl -sf -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" {{ console_mgmt_base_url }}/management/api/v2/pageservers/${INSTANCE_ID} -o /dev/null; then
# not registered, so register it now
ID=$(curl -sf -X POST -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" {{ console_mgmt_base_url }}/management/api/v2/pageservers -d@/tmp/payload | jq -r '.id')
# init pageserver
sudo -u pageserver /usr/local/bin/pageserver -c "id=${ID}" -c "pg_distrib_dir='/usr/local'" --init -D /storage/pageserver/data
fi

View File

@@ -0,0 +1,31 @@
#!/bin/sh
# fetch params from meta-data service
INSTANCE_ID=$(curl -s http://169.254.169.254/latest/meta-data/instance-id)
AZ_ID=$(curl -s http://169.254.169.254/latest/meta-data/placement/availability-zone)
# store fqdn hostname in var
HOST=$(hostname -f)
cat <<EOF | tee /tmp/payload
{
"version": 1,
"host": "${HOST}",
"port": 6500,
"http_port": 7676,
"region_id": "{{ console_region_id }}",
"instance_id": "${INSTANCE_ID}",
"availability_zone_id": "${AZ_ID}",
"active": false
}
EOF
# check if safekeeper already registered or not
if ! curl -sf -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" {{ console_mgmt_base_url }}/management/api/v2/safekeepers/${INSTANCE_ID} -o /dev/null; then
# not registered, so register it now
ID=$(curl -sf -X POST -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" {{ console_mgmt_base_url }}/management/api/v2/safekeepers -d@/tmp/payload | jq -r '.id')
# init safekeeper
sudo -u safekeeper /usr/local/bin/safekeeper --id ${ID} --init -D /storage/safekeeper/data
fi

2
.github/ansible/ssm_config vendored Normal file
View File

@@ -0,0 +1,2 @@
ansible_connection: aws_ssm
ansible_python_interpreter: /usr/bin/python3

View File

@@ -0,0 +1,36 @@
storage:
vars:
bucket_name: neon-dev-storage-eu-west-1
bucket_region: eu-west-1
console_mgmt_base_url: http://console-staging.local
broker_endpoint: http://storage-broker-lb.zeta.eu-west-1.internal.aws.neon.build:50051
pageserver_config_stub:
pg_distrib_dir: /usr/local
metric_collection_endpoint: http://console-staging.local/billing/api/v1/usage_events
metric_collection_interval: 10min
remote_storage:
bucket_name: "{{ bucket_name }}"
bucket_region: "{{ bucket_region }}"
prefix_in_bucket: "pageserver/v1"
safekeeper_s3_prefix: safekeeper/v1/wal
hostname_suffix: ""
remote_user: ssm-user
ansible_aws_ssm_region: eu-west-1
ansible_aws_ssm_bucket_name: neon-dev-storage-eu-west-1
console_region_id: aws-eu-west-1
sentry_environment: staging
children:
pageservers:
hosts:
pageserver-0.eu-west-1.aws.neon.build:
ansible_host: i-01d496c5041c7f34c
safekeepers:
hosts:
safekeeper-0.eu-west-1.aws.neon.build:
ansible_host: i-05226ef85722831bf
safekeeper-1.eu-west-1.aws.neon.build:
ansible_host: i-06969ee1bf2958bfc
safekeeper-2.eu-west-1.aws.neon.build:
ansible_host: i-087892e9625984a0b

View File

@@ -0,0 +1,42 @@
storage:
vars:
bucket_name: neon-staging-storage-us-east-2
bucket_region: us-east-2
console_mgmt_base_url: http://console-staging.local
broker_endpoint: http://storage-broker-lb.beta.us-east-2.internal.aws.neon.build:50051
pageserver_config_stub:
pg_distrib_dir: /usr/local
metric_collection_endpoint: http://console-staging.local/billing/api/v1/usage_events
metric_collection_interval: 10min
remote_storage:
bucket_name: "{{ bucket_name }}"
bucket_region: "{{ bucket_region }}"
prefix_in_bucket: "pageserver/v1"
safekeeper_s3_prefix: safekeeper/v1/wal
hostname_suffix: ""
remote_user: ssm-user
ansible_aws_ssm_region: us-east-2
ansible_aws_ssm_bucket_name: neon-staging-storage-us-east-2
console_region_id: aws-us-east-2
sentry_environment: staging
children:
pageservers:
hosts:
pageserver-0.us-east-2.aws.neon.build:
ansible_host: i-0c3e70929edb5d691
pageserver-1.us-east-2.aws.neon.build:
ansible_host: i-0565a8b4008aa3f40
pageserver-2.us-east-2.aws.neon.build:
ansible_host: i-01e31cdf7e970586a
pageserver-3.us-east-2.aws.neon.build:
ansible_host: i-0602a0291365ef7cc
safekeepers:
hosts:
safekeeper-0.us-east-2.aws.neon.build:
ansible_host: i-027662bd552bf5db0
safekeeper-1.us-east-2.aws.neon.build:
ansible_host: i-0171efc3604a7b907
safekeeper-2.us-east-2.aws.neon.build:
ansible_host: i-0de0b03a51676a6ce

View File

@@ -0,0 +1,18 @@
[Unit]
Description=Neon pageserver
After=network.target auditd.service
[Service]
Type=simple
User=pageserver
Environment=RUST_BACKTRACE=1 NEON_REPO_DIR=/storage/pageserver LD_LIBRARY_PATH=/usr/local/v14/lib SENTRY_DSN={{ SENTRY_URL_PAGESERVER }} SENTRY_ENVIRONMENT={{ sentry_environment }}
ExecStart=/usr/local/bin/pageserver -c "pg_distrib_dir='/usr/local'" -c "listen_pg_addr='0.0.0.0:6400'" -c "listen_http_addr='0.0.0.0:9898'" -c "broker_endpoint='{{ broker_endpoint }}'" -D /storage/pageserver/data
ExecReload=/bin/kill -HUP $MAINPID
KillMode=mixed
KillSignal=SIGINT
Restart=on-failure
TimeoutSec=10
LimitNOFILE=30000000
[Install]
WantedBy=multi-user.target

View File

@@ -0,0 +1,18 @@
[Unit]
Description=Neon safekeeper
After=network.target auditd.service
[Service]
Type=simple
User=safekeeper
Environment=RUST_BACKTRACE=1 NEON_REPO_DIR=/storage/safekeeper/data LD_LIBRARY_PATH=/usr/local/v14/lib SENTRY_DSN={{ SENTRY_URL_SAFEKEEPER }} SENTRY_ENVIRONMENT={{ sentry_environment }}
ExecStart=/usr/local/bin/safekeeper -l {{ inventory_hostname }}{{ hostname_suffix }}:6500 --listen-http {{ inventory_hostname }}{{ hostname_suffix }}:7676 -D /storage/safekeeper/data --broker-endpoint={{ broker_endpoint }} --remote-storage='{bucket_name="{{bucket_name}}", bucket_region="{{bucket_region}}", prefix_in_bucket="{{ safekeeper_s3_prefix }}"}'
ExecReload=/bin/kill -HUP $MAINPID
KillMode=mixed
KillSignal=SIGINT
Restart=on-failure
TimeoutSec=10
LimitNOFILE=30000000
[Install]
WantedBy=multi-user.target

View File

@@ -0,0 +1 @@
{{ pageserver_config | sivel.toiletwater.to_toml }}

View File

@@ -0,0 +1,61 @@
# Helm chart values for neon-proxy-scram.
# This is a YAML-formatted file.
image:
repository: neondatabase/neon
settings:
authBackend: "console"
authEndpoint: "http://console-staging.local/management/api/v2"
domain: "*.eu-west-1.aws.neon.build"
sentryEnvironment: "staging"
wssPort: 8443
metricCollectionEndpoint: "http://console-staging.local/billing/api/v1/usage_events"
metricCollectionInterval: "1min"
# -- Additional labels for neon-proxy pods
podLabels:
zenith_service: proxy-scram
zenith_env: dev
zenith_region: eu-west-1
zenith_region_slug: eu-west-1
exposedService:
annotations:
service.beta.kubernetes.io/aws-load-balancer-type: external
service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
service.beta.kubernetes.io/aws-load-balancer-scheme: internet-facing
external-dns.alpha.kubernetes.io/hostname: eu-west-1.aws.neon.build
httpsPort: 443
#metrics:
# enabled: true
# serviceMonitor:
# enabled: true
# selector:
# release: kube-prometheus-stack
extraManifests:
- apiVersion: operator.victoriametrics.com/v1beta1
kind: VMServiceScrape
metadata:
name: "{{ include \"neon-proxy.fullname\" . }}"
labels:
helm.sh/chart: neon-proxy-{{ .Chart.Version }}
app.kubernetes.io/name: neon-proxy
app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
app.kubernetes.io/managed-by: Helm
namespace: "{{ .Release.Namespace }}"
spec:
selector:
matchLabels:
app.kubernetes.io/name: "neon-proxy"
endpoints:
- port: http
path: /metrics
interval: 10s
scrapeTimeout: 10s
namespaceSelector:
matchNames:
- "{{ .Release.Namespace }}"

View File

@@ -0,0 +1,52 @@
# Helm chart values for neon-storage-broker
podLabels:
neon_env: staging
neon_service: storage-broker
# Use L4 LB
service:
# service.annotations -- Annotations to add to the service
annotations:
service.beta.kubernetes.io/aws-load-balancer-type: external # use newer AWS Load Balancer Controller
service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
service.beta.kubernetes.io/aws-load-balancer-scheme: internal # deploy LB to private subnet
# assign service to this name at external-dns
external-dns.alpha.kubernetes.io/hostname: storage-broker-lb.zeta.eu-west-1.internal.aws.neon.build
# service.type -- Service type
type: LoadBalancer
# service.port -- broker listen port
port: 50051
ingress:
enabled: false
metrics:
enabled: false
extraManifests:
- apiVersion: operator.victoriametrics.com/v1beta1
kind: VMServiceScrape
metadata:
name: "{{ include \"neon-storage-broker.fullname\" . }}"
labels:
helm.sh/chart: neon-storage-broker-{{ .Chart.Version }}
app.kubernetes.io/name: neon-storage-broker
app.kubernetes.io/instance: neon-storage-broker
app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
app.kubernetes.io/managed-by: Helm
namespace: "{{ .Release.Namespace }}"
spec:
selector:
matchLabels:
app.kubernetes.io/name: "neon-storage-broker"
endpoints:
- port: broker
path: /metrics
interval: 10s
scrapeTimeout: 10s
namespaceSelector:
matchNames:
- "{{ .Release.Namespace }}"
settings:
sentryEnvironment: "staging"

View File

@@ -0,0 +1,67 @@
# Helm chart values for neon-proxy-link.
# This is a YAML-formatted file.
image:
repository: neondatabase/neon
settings:
authBackend: "link"
authEndpoint: "https://console.stage.neon.tech/authenticate_proxy_request/"
uri: "https://console.stage.neon.tech/psql_session/"
sentryEnvironment: "staging"
metricCollectionEndpoint: "http://console-staging.local/billing/api/v1/usage_events"
metricCollectionInterval: "1min"
# -- Additional labels for neon-proxy-link pods
podLabels:
zenith_service: proxy
zenith_env: dev
zenith_region: us-east-2
zenith_region_slug: us-east-2
service:
type: LoadBalancer
annotations:
service.beta.kubernetes.io/aws-load-balancer-type: external
service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
service.beta.kubernetes.io/aws-load-balancer-scheme: internal
external-dns.alpha.kubernetes.io/hostname: neon-proxy-link-mgmt.beta.us-east-2.aws.neon.build
exposedService:
annotations:
service.beta.kubernetes.io/aws-load-balancer-type: external
service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
service.beta.kubernetes.io/aws-load-balancer-scheme: internet-facing
external-dns.alpha.kubernetes.io/hostname: neon-proxy-link.beta.us-east-2.aws.neon.build
#metrics:
# enabled: true
# serviceMonitor:
# enabled: true
# selector:
# release: kube-prometheus-stack
extraManifests:
- apiVersion: operator.victoriametrics.com/v1beta1
kind: VMServiceScrape
metadata:
name: "{{ include \"neon-proxy.fullname\" . }}"
labels:
helm.sh/chart: neon-proxy-{{ .Chart.Version }}
app.kubernetes.io/name: neon-proxy
app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
app.kubernetes.io/managed-by: Helm
namespace: "{{ .Release.Namespace }}"
spec:
selector:
matchLabels:
app.kubernetes.io/name: "neon-proxy"
endpoints:
- port: http
path: /metrics
interval: 10s
scrapeTimeout: 10s
namespaceSelector:
matchNames:
- "{{ .Release.Namespace }}"

View File

@@ -0,0 +1,61 @@
# Helm chart values for neon-proxy-scram.
# This is a YAML-formatted file.
image:
repository: neondatabase/neon
settings:
authBackend: "console"
authEndpoint: "http://console-staging.local/management/api/v2"
domain: "*.cloud.stage.neon.tech"
sentryEnvironment: "staging"
wssPort: 8443
metricCollectionEndpoint: "http://console-staging.local/billing/api/v1/usage_events"
metricCollectionInterval: "1min"
# -- Additional labels for neon-proxy pods
podLabels:
zenith_service: proxy-scram-legacy
zenith_env: dev
zenith_region: us-east-2
zenith_region_slug: us-east-2
exposedService:
annotations:
service.beta.kubernetes.io/aws-load-balancer-type: external
service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
service.beta.kubernetes.io/aws-load-balancer-scheme: internet-facing
external-dns.alpha.kubernetes.io/hostname: neon-proxy-scram-legacy.beta.us-east-2.aws.neon.build
httpsPort: 443
#metrics:
# enabled: true
# serviceMonitor:
# enabled: true
# selector:
# release: kube-prometheus-stack
extraManifests:
- apiVersion: operator.victoriametrics.com/v1beta1
kind: VMServiceScrape
metadata:
name: "{{ include \"neon-proxy.fullname\" . }}"
labels:
helm.sh/chart: neon-proxy-{{ .Chart.Version }}
app.kubernetes.io/name: neon-proxy
app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
app.kubernetes.io/managed-by: Helm
namespace: "{{ .Release.Namespace }}"
spec:
selector:
matchLabels:
app.kubernetes.io/name: "neon-proxy"
endpoints:
- port: http
path: /metrics
interval: 10s
scrapeTimeout: 10s
namespaceSelector:
matchNames:
- "{{ .Release.Namespace }}"

View File

@@ -0,0 +1,61 @@
# Helm chart values for neon-proxy-scram.
# This is a YAML-formatted file.
image:
repository: neondatabase/neon
settings:
authBackend: "console"
authEndpoint: "http://console-staging.local/management/api/v2"
domain: "*.us-east-2.aws.neon.build"
sentryEnvironment: "staging"
wssPort: 8443
metricCollectionEndpoint: "http://console-staging.local/billing/api/v1/usage_events"
metricCollectionInterval: "1min"
# -- Additional labels for neon-proxy pods
podLabels:
zenith_service: proxy-scram
zenith_env: dev
zenith_region: us-east-2
zenith_region_slug: us-east-2
exposedService:
annotations:
service.beta.kubernetes.io/aws-load-balancer-type: external
service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
service.beta.kubernetes.io/aws-load-balancer-scheme: internet-facing
external-dns.alpha.kubernetes.io/hostname: us-east-2.aws.neon.build
httpsPort: 443
#metrics:
# enabled: true
# serviceMonitor:
# enabled: true
# selector:
# release: kube-prometheus-stack
extraManifests:
- apiVersion: operator.victoriametrics.com/v1beta1
kind: VMServiceScrape
metadata:
name: "{{ include \"neon-proxy.fullname\" . }}"
labels:
helm.sh/chart: neon-proxy-{{ .Chart.Version }}
app.kubernetes.io/name: neon-proxy
app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
app.kubernetes.io/managed-by: Helm
namespace: "{{ .Release.Namespace }}"
spec:
selector:
matchLabels:
app.kubernetes.io/name: "neon-proxy"
endpoints:
- port: http
path: /metrics
interval: 10s
scrapeTimeout: 10s
namespaceSelector:
matchNames:
- "{{ .Release.Namespace }}"

View File

@@ -0,0 +1,52 @@
# Helm chart values for neon-storage-broker
podLabels:
neon_env: staging
neon_service: storage-broker
# Use L4 LB
service:
# service.annotations -- Annotations to add to the service
annotations:
service.beta.kubernetes.io/aws-load-balancer-type: external # use newer AWS Load Balancer Controller
service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
service.beta.kubernetes.io/aws-load-balancer-scheme: internal # deploy LB to private subnet
# assign service to this name at external-dns
external-dns.alpha.kubernetes.io/hostname: storage-broker-lb.beta.us-east-2.internal.aws.neon.build
# service.type -- Service type
type: LoadBalancer
# service.port -- broker listen port
port: 50051
ingress:
enabled: false
metrics:
enabled: false
extraManifests:
- apiVersion: operator.victoriametrics.com/v1beta1
kind: VMServiceScrape
metadata:
name: "{{ include \"neon-storage-broker.fullname\" . }}"
labels:
helm.sh/chart: neon-storage-broker-{{ .Chart.Version }}
app.kubernetes.io/name: neon-storage-broker
app.kubernetes.io/instance: neon-storage-broker
app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
app.kubernetes.io/managed-by: Helm
namespace: "{{ .Release.Namespace }}"
spec:
selector:
matchLabels:
app.kubernetes.io/name: "neon-storage-broker"
endpoints:
- port: broker
path: /metrics
interval: 10s
scrapeTimeout: 10s
namespaceSelector:
matchNames:
- "{{ .Release.Namespace }}"
settings:
sentryEnvironment: "staging"

View File

@@ -0,0 +1,61 @@
# Helm chart values for neon-proxy-scram.
# This is a YAML-formatted file.
image:
repository: neondatabase/neon
settings:
authBackend: "console"
authEndpoint: "http://console-release.local/management/api/v2"
domain: "*.ap-southeast-1.aws.neon.tech"
sentryEnvironment: "production"
wssPort: 8443
metricCollectionEndpoint: "http://console-release.local/billing/api/v1/usage_events"
metricCollectionInterval: "10min"
# -- Additional labels for neon-proxy pods
podLabels:
zenith_service: proxy-scram
zenith_env: prod
zenith_region: ap-southeast-1
zenith_region_slug: ap-southeast-1
exposedService:
annotations:
service.beta.kubernetes.io/aws-load-balancer-type: external
service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
service.beta.kubernetes.io/aws-load-balancer-scheme: internet-facing
external-dns.alpha.kubernetes.io/hostname: ap-southeast-1.aws.neon.tech
httpsPort: 443
#metrics:
# enabled: true
# serviceMonitor:
# enabled: true
# selector:
# release: kube-prometheus-stack
extraManifests:
- apiVersion: operator.victoriametrics.com/v1beta1
kind: VMServiceScrape
metadata:
name: "{{ include \"neon-proxy.fullname\" . }}"
labels:
helm.sh/chart: neon-proxy-{{ .Chart.Version }}
app.kubernetes.io/name: neon-proxy
app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
app.kubernetes.io/managed-by: Helm
namespace: "{{ .Release.Namespace }}"
spec:
selector:
matchLabels:
app.kubernetes.io/name: "neon-proxy"
endpoints:
- port: http
path: /metrics
interval: 10s
scrapeTimeout: 10s
namespaceSelector:
matchNames:
- "{{ .Release.Namespace }}"

View File

@@ -0,0 +1,52 @@
# Helm chart values for neon-storage-broker
podLabels:
neon_env: production
neon_service: storage-broker
# Use L4 LB
service:
# service.annotations -- Annotations to add to the service
annotations:
service.beta.kubernetes.io/aws-load-balancer-type: external # use newer AWS Load Balancer Controller
service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
service.beta.kubernetes.io/aws-load-balancer-scheme: internal # deploy LB to private subnet
# assign service to this name at external-dns
external-dns.alpha.kubernetes.io/hostname: storage-broker-lb.epsilon.ap-southeast-1.internal.aws.neon.tech
# service.type -- Service type
type: LoadBalancer
# service.port -- broker listen port
port: 50051
ingress:
enabled: false
metrics:
enabled: false
extraManifests:
- apiVersion: operator.victoriametrics.com/v1beta1
kind: VMServiceScrape
metadata:
name: "{{ include \"neon-storage-broker.fullname\" . }}"
labels:
helm.sh/chart: neon-storage-broker-{{ .Chart.Version }}
app.kubernetes.io/name: neon-storage-broker
app.kubernetes.io/instance: neon-storage-broker
app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
app.kubernetes.io/managed-by: Helm
namespace: "{{ .Release.Namespace }}"
spec:
selector:
matchLabels:
app.kubernetes.io/name: "neon-storage-broker"
endpoints:
- port: broker
path: /metrics
interval: 10s
scrapeTimeout: 10s
namespaceSelector:
matchNames:
- "{{ .Release.Namespace }}"
settings:
sentryEnvironment: "production"

View File

@@ -0,0 +1,61 @@
# Helm chart values for neon-proxy-scram.
# This is a YAML-formatted file.
image:
repository: neondatabase/neon
settings:
authBackend: "console"
authEndpoint: "http://console-release.local/management/api/v2"
domain: "*.eu-central-1.aws.neon.tech"
sentryEnvironment: "production"
wssPort: 8443
metricCollectionEndpoint: "http://console-release.local/billing/api/v1/usage_events"
metricCollectionInterval: "10min"
# -- Additional labels for neon-proxy pods
podLabels:
zenith_service: proxy-scram
zenith_env: prod
zenith_region: eu-central-1
zenith_region_slug: eu-central-1
exposedService:
annotations:
service.beta.kubernetes.io/aws-load-balancer-type: external
service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
service.beta.kubernetes.io/aws-load-balancer-scheme: internet-facing
external-dns.alpha.kubernetes.io/hostname: eu-central-1.aws.neon.tech
httpsPort: 443
#metrics:
# enabled: true
# serviceMonitor:
# enabled: true
# selector:
# release: kube-prometheus-stack
extraManifests:
- apiVersion: operator.victoriametrics.com/v1beta1
kind: VMServiceScrape
metadata:
name: "{{ include \"neon-proxy.fullname\" . }}"
labels:
helm.sh/chart: neon-proxy-{{ .Chart.Version }}
app.kubernetes.io/name: neon-proxy
app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
app.kubernetes.io/managed-by: Helm
namespace: "{{ .Release.Namespace }}"
spec:
selector:
matchLabels:
app.kubernetes.io/name: "neon-proxy"
endpoints:
- port: http
path: /metrics
interval: 10s
scrapeTimeout: 10s
namespaceSelector:
matchNames:
- "{{ .Release.Namespace }}"

View File

@@ -0,0 +1,52 @@
# Helm chart values for neon-storage-broker
podLabels:
neon_env: production
neon_service: storage-broker
# Use L4 LB
service:
# service.annotations -- Annotations to add to the service
annotations:
service.beta.kubernetes.io/aws-load-balancer-type: external # use newer AWS Load Balancer Controller
service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
service.beta.kubernetes.io/aws-load-balancer-scheme: internal # deploy LB to private subnet
# assign service to this name at external-dns
external-dns.alpha.kubernetes.io/hostname: storage-broker-lb.gamma.eu-central-1.internal.aws.neon.tech
# service.type -- Service type
type: LoadBalancer
# service.port -- broker listen port
port: 50051
ingress:
enabled: false
metrics:
enabled: false
extraManifests:
- apiVersion: operator.victoriametrics.com/v1beta1
kind: VMServiceScrape
metadata:
name: "{{ include \"neon-storage-broker.fullname\" . }}"
labels:
helm.sh/chart: neon-storage-broker-{{ .Chart.Version }}
app.kubernetes.io/name: neon-storage-broker
app.kubernetes.io/instance: neon-storage-broker
app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
app.kubernetes.io/managed-by: Helm
namespace: "{{ .Release.Namespace }}"
spec:
selector:
matchLabels:
app.kubernetes.io/name: "neon-storage-broker"
endpoints:
- port: broker
path: /metrics
interval: 10s
scrapeTimeout: 10s
namespaceSelector:
matchNames:
- "{{ .Release.Namespace }}"
settings:
sentryEnvironment: "production"

View File

@@ -0,0 +1,61 @@
# Helm chart values for neon-proxy-scram.
# This is a YAML-formatted file.
image:
repository: neondatabase/neon
settings:
authBackend: "console"
authEndpoint: "http://console-release.local/management/api/v2"
domain: "*.us-east-2.aws.neon.tech"
sentryEnvironment: "production"
wssPort: 8443
metricCollectionEndpoint: "http://console-release.local/billing/api/v1/usage_events"
metricCollectionInterval: "10min"
# -- Additional labels for neon-proxy pods
podLabels:
zenith_service: proxy-scram
zenith_env: prod
zenith_region: us-east-2
zenith_region_slug: us-east-2
exposedService:
annotations:
service.beta.kubernetes.io/aws-load-balancer-type: external
service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
service.beta.kubernetes.io/aws-load-balancer-scheme: internet-facing
external-dns.alpha.kubernetes.io/hostname: us-east-2.aws.neon.tech
httpsPort: 443
#metrics:
# enabled: true
# serviceMonitor:
# enabled: true
# selector:
# release: kube-prometheus-stack
extraManifests:
- apiVersion: operator.victoriametrics.com/v1beta1
kind: VMServiceScrape
metadata:
name: "{{ include \"neon-proxy.fullname\" . }}"
labels:
helm.sh/chart: neon-proxy-{{ .Chart.Version }}
app.kubernetes.io/name: neon-proxy
app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
app.kubernetes.io/managed-by: Helm
namespace: "{{ .Release.Namespace }}"
spec:
selector:
matchLabels:
app.kubernetes.io/name: "neon-proxy"
endpoints:
- port: http
path: /metrics
interval: 10s
scrapeTimeout: 10s
namespaceSelector:
matchNames:
- "{{ .Release.Namespace }}"

View File

@@ -0,0 +1,52 @@
# Helm chart values for neon-storage-broker
podLabels:
neon_env: production
neon_service: storage-broker
# Use L4 LB
service:
# service.annotations -- Annotations to add to the service
annotations:
service.beta.kubernetes.io/aws-load-balancer-type: external # use newer AWS Load Balancer Controller
service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
service.beta.kubernetes.io/aws-load-balancer-scheme: internal # deploy LB to private subnet
# assign service to this name at external-dns
external-dns.alpha.kubernetes.io/hostname: storage-broker-lb.delta.us-east-2.internal.aws.neon.tech
# service.type -- Service type
type: LoadBalancer
# service.port -- broker listen port
port: 50051
ingress:
enabled: false
metrics:
enabled: false
extraManifests:
- apiVersion: operator.victoriametrics.com/v1beta1
kind: VMServiceScrape
metadata:
name: "{{ include \"neon-storage-broker.fullname\" . }}"
labels:
helm.sh/chart: neon-storage-broker-{{ .Chart.Version }}
app.kubernetes.io/name: neon-storage-broker
app.kubernetes.io/instance: neon-storage-broker
app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
app.kubernetes.io/managed-by: Helm
namespace: "{{ .Release.Namespace }}"
spec:
selector:
matchLabels:
app.kubernetes.io/name: "neon-storage-broker"
endpoints:
- port: broker
path: /metrics
interval: 10s
scrapeTimeout: 10s
namespaceSelector:
matchNames:
- "{{ .Release.Namespace }}"
settings:
sentryEnvironment: "production"

View File

@@ -0,0 +1,61 @@
# Helm chart values for neon-proxy-scram.
# This is a YAML-formatted file.
image:
repository: neondatabase/neon
settings:
authBackend: "console"
authEndpoint: "http://console-release.local/management/api/v2"
domain: "*.us-west-2.aws.neon.tech"
sentryEnvironment: "production"
wssPort: 8443
metricCollectionEndpoint: "http://console-release.local/billing/api/v1/usage_events"
metricCollectionInterval: "10min"
# -- Additional labels for neon-proxy pods
podLabels:
zenith_service: proxy-scram
zenith_env: prod
zenith_region: us-west-2
zenith_region_slug: us-west-2
exposedService:
annotations:
service.beta.kubernetes.io/aws-load-balancer-type: external
service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
service.beta.kubernetes.io/aws-load-balancer-scheme: internet-facing
external-dns.alpha.kubernetes.io/hostname: us-west-2.aws.neon.tech
httpsPort: 443
#metrics:
# enabled: true
# serviceMonitor:
# enabled: true
# selector:
# release: kube-prometheus-stack
extraManifests:
- apiVersion: operator.victoriametrics.com/v1beta1
kind: VMServiceScrape
metadata:
name: "{{ include \"neon-proxy.fullname\" . }}"
labels:
helm.sh/chart: neon-proxy-{{ .Chart.Version }}
app.kubernetes.io/name: neon-proxy
app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
app.kubernetes.io/managed-by: Helm
namespace: "{{ .Release.Namespace }}"
spec:
selector:
matchLabels:
app.kubernetes.io/name: "neon-proxy"
endpoints:
- port: http
path: /metrics
interval: 10s
scrapeTimeout: 10s
namespaceSelector:
matchNames:
- "{{ .Release.Namespace }}"

View File

@@ -0,0 +1,52 @@
# Helm chart values for neon-storage-broker
podLabels:
neon_env: production
neon_service: storage-broker
# Use L4 LB
service:
# service.annotations -- Annotations to add to the service
annotations:
service.beta.kubernetes.io/aws-load-balancer-type: external # use newer AWS Load Balancer Controller
service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
service.beta.kubernetes.io/aws-load-balancer-scheme: internal # deploy LB to private subnet
# assign service to this name at external-dns
external-dns.alpha.kubernetes.io/hostname: storage-broker-lb.eta.us-west-2.internal.aws.neon.tech
# service.type -- Service type
type: LoadBalancer
# service.port -- broker listen port
port: 50051
ingress:
enabled: false
metrics:
enabled: false
extraManifests:
- apiVersion: operator.victoriametrics.com/v1beta1
kind: VMServiceScrape
metadata:
name: "{{ include \"neon-storage-broker.fullname\" . }}"
labels:
helm.sh/chart: neon-storage-broker-{{ .Chart.Version }}
app.kubernetes.io/name: neon-storage-broker
app.kubernetes.io/instance: neon-storage-broker
app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
app.kubernetes.io/managed-by: Helm
namespace: "{{ .Release.Namespace }}"
spec:
selector:
matchLabels:
app.kubernetes.io/name: "neon-storage-broker"
endpoints:
- port: broker
path: /metrics
interval: 10s
scrapeTimeout: 10s
namespaceSelector:
matchNames:
- "{{ .Release.Namespace }}"
settings:
sentryEnvironment: "production"

View File

@@ -0,0 +1,56 @@
# Helm chart values for neon-storage-broker
podLabels:
neon_env: production
neon_service: storage-broker
# Use L4 LB
service:
# service.annotations -- Annotations to add to the service
annotations:
service.beta.kubernetes.io/aws-load-balancer-type: external # use newer AWS Load Balancer Controller
service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
service.beta.kubernetes.io/aws-load-balancer-scheme: internal # deploy LB to private subnet
# assign service to this name at external-dns
external-dns.alpha.kubernetes.io/hostname: storage-broker.prod.local
# service.type -- Service type
type: LoadBalancer
# service.port -- broker listen port
port: 50051
ingress:
enabled: false
metrics:
enabled: true
serviceMonitor:
enabled: true
selector:
release: kube-prometheus-stack
extraManifests:
- apiVersion: operator.victoriametrics.com/v1beta1
kind: VMServiceScrape
metadata:
name: "{{ include \"neon-storage-broker.fullname\" . }}"
labels:
helm.sh/chart: neon-storage-broker-{{ .Chart.Version }}
app.kubernetes.io/name: neon-storage-broker
app.kubernetes.io/instance: neon-storage-broker
app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
app.kubernetes.io/managed-by: Helm
namespace: "{{ .Release.Namespace }}"
spec:
selector:
matchLabels:
app.kubernetes.io/name: "neon-storage-broker"
endpoints:
- port: broker
path: /metrics
interval: 10s
scrapeTimeout: 10s
namespaceSelector:
matchNames:
- "{{ .Release.Namespace }}"
settings:
sentryEnvironment: "production"

View File

@@ -0,0 +1,54 @@
settings:
authBackend: "console"
authEndpoint: "http://console-release.local/management/api/v2"
domain: "*.cloud.neon.tech"
sentryEnvironment: "production"
wssPort: 8443
metricCollectionEndpoint: "http://console-release.local/billing/api/v1/usage_events"
metricCollectionInterval: "10min"
podLabels:
zenith_service: proxy-scram
zenith_env: production
zenith_region: us-west-2
zenith_region_slug: oregon
exposedService:
annotations:
service.beta.kubernetes.io/aws-load-balancer-type: external
service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
service.beta.kubernetes.io/aws-load-balancer-scheme: internet-facing
external-dns.alpha.kubernetes.io/hostname: '*.cloud.neon.tech'
httpsPort: 443
metrics:
enabled: true
serviceMonitor:
enabled: true
selector:
release: kube-prometheus-stack
extraManifests:
- apiVersion: operator.victoriametrics.com/v1beta1
kind: VMServiceScrape
metadata:
name: "{{ include \"neon-proxy.fullname\" . }}"
labels:
helm.sh/chart: neon-proxy-{{ .Chart.Version }}
app.kubernetes.io/name: neon-proxy
app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
app.kubernetes.io/managed-by: Helm
namespace: "{{ .Release.Namespace }}"
spec:
selector:
matchLabels:
app.kubernetes.io/name: "neon-proxy"
endpoints:
- port: http
path: /metrics
interval: 10s
scrapeTimeout: 10s
namespaceSelector:
matchNames:
- "{{ .Release.Namespace }}"

View File

@@ -0,0 +1,59 @@
settings:
authBackend: "link"
authEndpoint: "https://console.neon.tech/authenticate_proxy_request/"
uri: "https://console.neon.tech/psql_session/"
sentryEnvironment: "production"
# -- Additional labels for zenith-proxy pods
podLabels:
zenith_service: proxy
zenith_env: production
zenith_region: us-west-2
zenith_region_slug: oregon
service:
annotations:
service.beta.kubernetes.io/aws-load-balancer-type: external
service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
service.beta.kubernetes.io/aws-load-balancer-scheme: internal
external-dns.alpha.kubernetes.io/hostname: proxy-release.local
type: LoadBalancer
exposedService:
annotations:
service.beta.kubernetes.io/aws-load-balancer-type: external
service.beta.kubernetes.io/aws-load-balancer-nlb-target-type: ip
service.beta.kubernetes.io/aws-load-balancer-scheme: internet-facing
external-dns.alpha.kubernetes.io/hostname: connect.neon.tech,pg.neon.tech
metrics:
enabled: true
serviceMonitor:
enabled: true
selector:
release: kube-prometheus-stack
extraManifests:
- apiVersion: operator.victoriametrics.com/v1beta1
kind: VMServiceScrape
metadata:
name: "{{ include \"neon-proxy.fullname\" . }}"
labels:
helm.sh/chart: neon-proxy-{{ .Chart.Version }}
app.kubernetes.io/name: neon-proxy
app.kubernetes.io/instance: "{{ include \"neon-proxy.fullname\" . }}"
app.kubernetes.io/version: "{{ .Chart.AppVersion }}"
app.kubernetes.io/managed-by: Helm
namespace: "{{ .Release.Namespace }}"
spec:
selector:
matchLabels:
app.kubernetes.io/name: "neon-proxy"
endpoints:
- port: http
path: /metrics
interval: 10s
scrapeTimeout: 10s
namespaceSelector:
matchNames:
- "{{ .Release.Namespace }}"

View File

@@ -1,31 +0,0 @@
name: Lint GitHub Workflows
on:
push:
branches:
- main
- release
paths:
- '.github/workflows/*.ya?ml'
pull_request:
paths:
- '.github/workflows/*.ya?ml'
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: ${{ github.event_name == 'pull_request' }}
jobs:
actionlint:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: reviewdog/action-actionlint@v1
env:
# SC2046 - Quote this to prevent word splitting. - https://www.shellcheck.net/wiki/SC2046
# SC2086 - Double quote to prevent globbing and word splitting. - https://www.shellcheck.net/wiki/SC2086
SHELLCHECK_OPTS: --exclude=SC2046,SC2086
with:
fail_on_error: true
filter_mode: nofilter
level: error

View File

@@ -1,118 +0,0 @@
name: Handle `approved-for-ci-run` label
# This workflow helps to run CI pipeline for PRs made by external contributors (from forks).
on:
pull_request_target:
branches:
- main
types:
# Default types that triggers a workflow ([1]):
# - [1] https://docs.github.com/en/actions/using-workflows/events-that-trigger-workflows#pull_request
- opened
- synchronize
- reopened
# Types that we wand to handle in addition to keep labels tidy:
- closed
# Actual magic happens here:
- labeled
concurrency:
group: ${{ github.workflow }}-${{ github.event.pull_request.number }}
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
PR_NUMBER: ${{ github.event.pull_request.number }}
BRANCH: "ci-run/pr-${{ github.event.pull_request.number }}"
# No permission for GITHUB_TOKEN by default; the **minimal required** set of permissions should be granted in each job.
permissions: {}
defaults:
run:
shell: bash -euo pipefail {0}
jobs:
remove-label:
# Remove `approved-for-ci-run` label if the workflow is triggered by changes in a PR.
# The PR should be reviewed and labelled manually again.
permissions:
pull-requests: write # For `gh pr edit`
if: |
contains(fromJSON('["opened", "synchronize", "reopened", "closed"]'), github.event.action) &&
contains(github.event.pull_request.labels.*.name, 'approved-for-ci-run')
runs-on: ubuntu-latest
steps:
- run: gh pr --repo "${GITHUB_REPOSITORY}" edit "${PR_NUMBER}" --remove-label "approved-for-ci-run"
create-or-update-pr-for-ci-run:
# Create local PR for an `approved-for-ci-run` labelled PR to run CI pipeline in it.
permissions:
pull-requests: write # for `gh pr edit`
# For `git push` and `gh pr create` we use CI_ACCESS_TOKEN
if: |
github.event.action == 'labeled' &&
contains(github.event.pull_request.labels.*.name, 'approved-for-ci-run')
runs-on: ubuntu-latest
steps:
- run: gh pr --repo "${GITHUB_REPOSITORY}" edit "${PR_NUMBER}" --remove-label "approved-for-ci-run"
- uses: actions/checkout@v3
with:
ref: main
token: ${{ secrets.CI_ACCESS_TOKEN }}
- run: gh pr checkout "${PR_NUMBER}"
- run: git checkout -b "${BRANCH}"
- run: git push --force origin "${BRANCH}"
- name: Create a Pull Request for CI run (if required)
env:
GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
run: |
cat << EOF > body.md
This Pull Request is created automatically to run the CI pipeline for #${PR_NUMBER}
Please do not alter or merge/close it.
Feel free to review/comment/discuss the original PR #${PR_NUMBER}.
EOF
ALREADY_CREATED="$(gh pr --repo ${GITHUB_REPOSITORY} list --head ${BRANCH} --base main --json number --jq '.[].number')"
if [ -z "${ALREADY_CREATED}" ]; then
gh pr --repo "${GITHUB_REPOSITORY}" create --title "CI run for PR #${PR_NUMBER}" \
--body-file "body.md" \
--head "${BRANCH}" \
--base "main" \
--draft
fi
cleanup:
# Close PRs and delete branchs if the original PR is closed.
permissions:
contents: write # for `--delete-branch` flag in `gh pr close`
pull-requests: write # for `gh pr close`
if: |
github.event.action == 'closed' &&
github.event.pull_request.head.repo.full_name != github.repository
runs-on: ubuntu-latest
steps:
- name: Close PR and delete `ci-run/pr-${{ env.PR_NUMBER }}` branch
run: |
CLOSED="$(gh pr --repo ${GITHUB_REPOSITORY} list --head ${BRANCH} --json 'closed' --jq '.[].closed')"
if [ "${CLOSED}" == "false" ]; then
gh pr --repo "${GITHUB_REPOSITORY}" close "${BRANCH}" --delete-branch
fi

View File

@@ -16,12 +16,12 @@ on:
workflow_dispatch: # adds ability to run this manually
inputs:
region_id:
description: 'Project region id. If not set, the default region will be used'
description: 'Use a particular region. If not set the default region will be used'
required: false
default: 'aws-us-east-2'
save_perf_report:
type: boolean
description: 'Publish perf report. If not set, the report will be published only for the main branch'
description: 'Publish perf report or not. If not set, the report is published only for the main branch'
required: false
defaults:
@@ -30,7 +30,7 @@ defaults:
concurrency:
# Allow only one workflow per any non-`main` branch.
group: ${{ github.workflow }}-${{ github.ref_name }}-${{ github.ref_name == 'main' && github.sha || 'anysha' }}
group: ${{ github.workflow }}-${{ github.ref }}-${{ github.ref == 'refs/heads/main' && github.sha || 'anysha' }}
cancel-in-progress: true
jobs:
@@ -42,7 +42,7 @@ jobs:
DEFAULT_PG_VERSION: 14
TEST_OUTPUT: /tmp/test_output
BUILD_TYPE: remote
SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref_name == 'main' ) }}
SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref == 'refs/heads/main' ) }}
PLATFORM: "neon-staging"
runs-on: [ self-hosted, us-east-2, x64 ]
@@ -92,8 +92,11 @@ jobs:
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
- name: Create Allure report
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
if: success() || failure()
uses: ./.github/actions/allure-report
with:
action: generate
build_type: ${{ env.BUILD_TYPE }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
@@ -104,86 +107,25 @@ jobs:
env:
SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
generate-matrices:
# Create matrices for the benchmarking jobs, so we run benchmarks on rds only once a week (on Saturday)
#
# Available platforms:
# - neon-captest-new: Freshly created project (1 CU)
# - neon-captest-freetier: Use freetier-sized compute (0.25 CU)
# - neon-captest-reuse: Reusing existing project
# - rds-aurora: Aurora Postgres Serverless v2 with autoscaling from 0.5 to 2 ACUs
# - rds-postgres: RDS Postgres db.m5.large instance (2 vCPU, 8 GiB) with gp3 EBS storage
runs-on: ubuntu-latest
outputs:
pgbench-compare-matrix: ${{ steps.pgbench-compare-matrix.outputs.matrix }}
olap-compare-matrix: ${{ steps.olap-compare-matrix.outputs.matrix }}
tpch-compare-matrix: ${{ steps.tpch-compare-matrix.outputs.matrix }}
steps:
- name: Generate matrix for pgbench benchmark
id: pgbench-compare-matrix
run: |
matrix='{
"platform": [
"neon-captest-new",
"neon-captest-reuse",
"neonvm-captest-new"
],
"db_size": [ "10gb" ],
"include": [{ "platform": "neon-captest-freetier", "db_size": "3gb" },
{ "platform": "neon-captest-new", "db_size": "50gb" },
{ "platform": "neonvm-captest-freetier", "db_size": "3gb" },
{ "platform": "neonvm-captest-new", "db_size": "50gb" }]
}'
if [ "$(date +%A)" = "Saturday" ]; then
matrix=$(echo "$matrix" | jq '.include += [{ "platform": "rds-postgres", "db_size": "10gb"},
{ "platform": "rds-aurora", "db_size": "50gb"}]')
fi
echo "matrix=$(echo "$matrix" | jq --compact-output '.')" >> $GITHUB_OUTPUT
- name: Generate matrix for OLAP benchmarks
id: olap-compare-matrix
run: |
matrix='{
"platform": [
"neon-captest-reuse"
]
}'
if [ "$(date +%A)" = "Saturday" ]; then
matrix=$(echo "$matrix" | jq '.include += [{ "platform": "rds-postgres" },
{ "platform": "rds-aurora" }]')
fi
echo "matrix=$(echo "$matrix" | jq --compact-output '.')" >> $GITHUB_OUTPUT
- name: Generate matrix for TPC-H benchmarks
id: tpch-compare-matrix
run: |
matrix='{
"platform": [
"neon-captest-reuse"
],
"scale": [
"10"
]
}'
if [ "$(date +%A)" = "Saturday" ]; then
matrix=$(echo "$matrix" | jq '.include += [{ "platform": "rds-postgres", "scale": "10" },
{ "platform": "rds-aurora", "scale": "10" }]')
fi
echo "matrix=$(echo "$matrix" | jq --compact-output '.')" >> $GITHUB_OUTPUT
pgbench-compare:
needs: [ generate-matrices ]
strategy:
fail-fast: false
matrix: ${{fromJson(needs.generate-matrices.outputs.pgbench-compare-matrix)}}
matrix:
# neon-captest-new: Run pgbench in a freshly created project
# neon-captest-reuse: Same, but reusing existing project
# neon-captest-prefetch: Same, with prefetching enabled (new project)
# rds-aurora: Aurora Postgres Serverless v2 with autoscaling from 0.5 to 2 ACUs
# rds-postgres: RDS Postgres db.m5.large instance (2 vCPU, 8 GiB) with gp3 EBS storage
platform: [ neon-captest-reuse, neon-captest-prefetch, rds-postgres ]
db_size: [ 10gb ]
runner: [ us-east-2 ]
include:
- platform: neon-captest-prefetch
db_size: 50gb
runner: us-east-2
- platform: rds-aurora
db_size: 50gb
runner: us-east-2
env:
TEST_PG_BENCH_DURATIONS_MATRIX: "60m"
@@ -192,16 +134,15 @@ jobs:
DEFAULT_PG_VERSION: 14
TEST_OUTPUT: /tmp/test_output
BUILD_TYPE: remote
SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref_name == 'main' ) }}
SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref == 'refs/heads/main' ) }}
PLATFORM: ${{ matrix.platform }}
runs-on: [ self-hosted, us-east-2, x64 ]
runs-on: [ self-hosted, "${{ matrix.runner }}", x64 ]
container:
image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
options: --init
# Increase timeout to 8h, default timeout is 6h
timeout-minutes: 480
timeout-minutes: 360 # 6h
steps:
- uses: actions/checkout@v3
@@ -219,15 +160,13 @@ jobs:
echo "${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin" >> $GITHUB_PATH
- name: Create Neon Project
if: contains(fromJson('["neon-captest-new", "neon-captest-freetier", "neonvm-captest-new", "neonvm-captest-freetier"]'), matrix.platform)
if: contains(fromJson('["neon-captest-new", "neon-captest-prefetch"]'), matrix.platform)
id: create-neon-project
uses: ./.github/actions/neon-project-create
with:
region_id: ${{ github.event.inputs.region_id || 'aws-us-east-2' }}
postgres_version: ${{ env.DEFAULT_PG_VERSION }}
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
compute_units: ${{ (matrix.platform == 'neon-captest-freetier' && '[0.25, 0.25]') || '[1, 1]' }}
provisioner: ${{ (contains(matrix.platform, 'neonvm-') && 'k8s-neonvm') || 'k8s-pod' }}
- name: Set up Connection String
id: set-up-connstr
@@ -236,7 +175,7 @@ jobs:
neon-captest-reuse)
CONNSTR=${{ secrets.BENCHMARK_CAPTEST_CONNSTR }}
;;
neon-captest-new | neon-captest-freetier | neonvm-captest-new | neonvm-captest-freetier)
neon-captest-new | neon-captest-prefetch)
CONNSTR=${{ steps.create-neon-project.outputs.dsn }}
;;
rds-aurora)
@@ -246,18 +185,25 @@ jobs:
CONNSTR=${{ secrets.BENCHMARK_RDS_POSTGRES_CONNSTR }}
;;
*)
echo >&2 "Unknown PLATFORM=${PLATFORM}"
echo 2>&1 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-reuse', 'neon-captest-new', 'neon-captest-prefetch', 'rds-aurora', or 'rds-postgres'"
exit 1
;;
esac
echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
QUERY="SELECT version();"
if [[ "${PLATFORM}" = "neon"* ]]; then
QUERY="${QUERY} SHOW neon.tenant_id; SHOW neon.timeline_id;"
fi
psql ${CONNSTR} -c "${QUERY}"
psql ${CONNSTR} -c "SELECT version();"
- name: Set database options
if: matrix.platform == 'neon-captest-prefetch'
run: |
DB_NAME=$(psql ${BENCHMARK_CONNSTR} --no-align --quiet -t -c "SELECT current_database()")
psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET enable_seqscan_prefetch=on"
psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET effective_io_concurrency=32"
psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET maintenance_io_concurrency=32"
env:
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
- name: Benchmark init
uses: ./.github/actions/run-python-test-set
@@ -306,8 +252,11 @@ jobs:
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
- name: Create Allure report
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
if: success() || failure()
uses: ./.github/actions/allure-report
with:
action: generate
build_type: ${{ env.BUILD_TYPE }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
@@ -326,19 +275,23 @@ jobs:
#
# *_CLICKBENCH_CONNSTR: Genuine ClickBench DB with ~100M rows
# *_CLICKBENCH_10M_CONNSTR: DB with the first 10M rows of ClickBench DB
if: ${{ !cancelled() }}
needs: [ generate-matrices, pgbench-compare ]
if: success() || failure()
needs: [ pgbench-compare ]
strategy:
fail-fast: false
matrix: ${{ fromJson(needs.generate-matrices.outputs.olap-compare-matrix) }}
matrix:
# neon-captest-prefetch: We have pre-created projects with prefetch enabled
# rds-aurora: Aurora Postgres Serverless v2 with autoscaling from 0.5 to 2 ACUs
# rds-postgres: RDS Postgres db.m5.large instance (2 vCPU, 8 GiB) with gp3 EBS storage
platform: [ neon-captest-prefetch, rds-postgres, rds-aurora ]
env:
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
DEFAULT_PG_VERSION: 14
TEST_OUTPUT: /tmp/test_output
BUILD_TYPE: remote
SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref_name == 'main' ) }}
SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref == 'refs/heads/main' ) }}
PLATFORM: ${{ matrix.platform }}
runs-on: [ self-hosted, us-east-2, x64 ]
@@ -346,6 +299,8 @@ jobs:
image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
options: --init
timeout-minutes: 360 # 6h
steps:
- uses: actions/checkout@v3
@@ -365,7 +320,7 @@ jobs:
id: set-up-connstr
run: |
case "${PLATFORM}" in
neon-captest-reuse)
neon-captest-prefetch)
CONNSTR=${{ secrets.BENCHMARK_CAPTEST_CLICKBENCH_10M_CONNSTR }}
;;
rds-aurora)
@@ -375,18 +330,25 @@ jobs:
CONNSTR=${{ secrets.BENCHMARK_RDS_POSTGRES_CLICKBENCH_10M_CONNSTR }}
;;
*)
echo >&2 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-reuse', 'rds-aurora', or 'rds-postgres'"
echo 2>&1 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-prefetch', 'rds-aurora', or 'rds-postgres'"
exit 1
;;
esac
echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
QUERY="SELECT version();"
if [[ "${PLATFORM}" = "neon"* ]]; then
QUERY="${QUERY} SHOW neon.tenant_id; SHOW neon.timeline_id;"
fi
psql ${CONNSTR} -c "${QUERY}"
psql ${CONNSTR} -c "SELECT version();"
- name: Set database options
if: matrix.platform == 'neon-captest-prefetch'
run: |
DB_NAME=$(psql ${BENCHMARK_CONNSTR} --no-align --quiet -t -c "SELECT current_database()")
psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET enable_seqscan_prefetch=on"
psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET effective_io_concurrency=32"
psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET maintenance_io_concurrency=32"
env:
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
- name: ClickBench benchmark
uses: ./.github/actions/run-python-test-set
@@ -400,11 +362,13 @@ jobs:
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
TEST_OLAP_SCALE: 10
- name: Create Allure report
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
if: success() || failure()
uses: ./.github/actions/allure-report
with:
action: generate
build_type: ${{ env.BUILD_TYPE }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
@@ -422,27 +386,32 @@ jobs:
# We might change it after https://github.com/neondatabase/neon/issues/2900.
#
# *_TPCH_S10_CONNSTR: DB generated with scale factor 10 (~10 GB)
if: ${{ !cancelled() }}
needs: [ generate-matrices, clickbench-compare ]
if: success() || failure()
needs: [ clickbench-compare ]
strategy:
fail-fast: false
matrix: ${{ fromJson(needs.generate-matrices.outputs.tpch-compare-matrix) }}
matrix:
# neon-captest-prefetch: We have pre-created projects with prefetch enabled
# rds-aurora: Aurora Postgres Serverless v2 with autoscaling from 0.5 to 2 ACUs
# rds-postgres: RDS Postgres db.m5.large instance (2 vCPU, 8 GiB) with gp3 EBS storage
platform: [ neon-captest-prefetch, rds-postgres, rds-aurora ]
env:
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
DEFAULT_PG_VERSION: 14
TEST_OUTPUT: /tmp/test_output
BUILD_TYPE: remote
SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref_name == 'main' ) }}
SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref == 'refs/heads/main' ) }}
PLATFORM: ${{ matrix.platform }}
TEST_OLAP_SCALE: ${{ matrix.scale }}
runs-on: [ self-hosted, us-east-2, x64 ]
container:
image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
options: --init
timeout-minutes: 360 # 6h
steps:
- uses: actions/checkout@v3
@@ -458,39 +427,39 @@ jobs:
${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin/pgbench --version
echo "${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin" >> $GITHUB_PATH
- name: Get Connstring Secret Name
- name: Set up Connection String
id: set-up-connstr
run: |
case "${PLATFORM}" in
neon-captest-reuse)
ENV_PLATFORM=CAPTEST_TPCH
neon-captest-prefetch)
CONNSTR=${{ secrets.BENCHMARK_CAPTEST_TPCH_S10_CONNSTR }}
;;
rds-aurora)
ENV_PLATFORM=RDS_AURORA_TPCH
CONNSTR=${{ secrets.BENCHMARK_RDS_AURORA_TPCH_S10_CONNSTR }}
;;
rds-postgres)
ENV_PLATFORM=RDS_AURORA_TPCH
CONNSTR=${{ secrets.BENCHMARK_RDS_POSTGRES_TPCH_S10_CONNSTR }}
;;
*)
echo >&2 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-reuse', 'rds-aurora', or 'rds-postgres'"
echo 2>&1 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-prefetch', 'rds-aurora', or 'rds-postgres'"
exit 1
;;
esac
CONNSTR_SECRET_NAME="BENCHMARK_${ENV_PLATFORM}_S${TEST_OLAP_SCALE}_CONNSTR"
echo "CONNSTR_SECRET_NAME=${CONNSTR_SECRET_NAME}" >> $GITHUB_ENV
- name: Set up Connection String
id: set-up-connstr
run: |
CONNSTR=${{ secrets[env.CONNSTR_SECRET_NAME] }}
echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
QUERY="SELECT version();"
if [[ "${PLATFORM}" = "neon"* ]]; then
QUERY="${QUERY} SHOW neon.tenant_id; SHOW neon.timeline_id;"
fi
psql ${CONNSTR} -c "${QUERY}"
psql ${CONNSTR} -c "SELECT version();"
- name: Set database options
if: matrix.platform == 'neon-captest-prefetch'
run: |
DB_NAME=$(psql ${BENCHMARK_CONNSTR} --no-align --quiet -t -c "SELECT current_database()")
psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET enable_seqscan_prefetch=on"
psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET effective_io_concurrency=32"
psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET maintenance_io_concurrency=32"
env:
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
- name: Run TPC-H benchmark
uses: ./.github/actions/run-python-test-set
@@ -504,11 +473,13 @@ jobs:
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
TEST_OLAP_SCALE: ${{ matrix.scale }}
- name: Create Allure report
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
if: success() || failure()
uses: ./.github/actions/allure-report
with:
action: generate
build_type: ${{ env.BUILD_TYPE }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
@@ -520,19 +491,23 @@ jobs:
SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
user-examples-compare:
if: ${{ !cancelled() }}
needs: [ generate-matrices, tpch-compare ]
if: success() || failure()
needs: [ tpch-compare ]
strategy:
fail-fast: false
matrix: ${{ fromJson(needs.generate-matrices.outputs.olap-compare-matrix) }}
matrix:
# neon-captest-prefetch: We have pre-created projects with prefetch enabled
# rds-aurora: Aurora Postgres Serverless v2 with autoscaling from 0.5 to 2 ACUs
# rds-postgres: RDS Postgres db.m5.large instance (2 vCPU, 8 GiB) with gp3 EBS storage
platform: [ neon-captest-prefetch, rds-postgres, rds-aurora ]
env:
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
DEFAULT_PG_VERSION: 14
TEST_OUTPUT: /tmp/test_output
BUILD_TYPE: remote
SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref_name == 'main' ) }}
SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref == 'refs/heads/main' ) }}
PLATFORM: ${{ matrix.platform }}
runs-on: [ self-hosted, us-east-2, x64 ]
@@ -540,6 +515,8 @@ jobs:
image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
options: --init
timeout-minutes: 360 # 6h
steps:
- uses: actions/checkout@v3
@@ -559,7 +536,7 @@ jobs:
id: set-up-connstr
run: |
case "${PLATFORM}" in
neon-captest-reuse)
neon-captest-prefetch)
CONNSTR=${{ secrets.BENCHMARK_USER_EXAMPLE_CAPTEST_CONNSTR }}
;;
rds-aurora)
@@ -569,18 +546,25 @@ jobs:
CONNSTR=${{ secrets.BENCHMARK_USER_EXAMPLE_RDS_POSTGRES_CONNSTR }}
;;
*)
echo >&2 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-reuse', 'rds-aurora', or 'rds-postgres'"
echo 2>&1 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-prefetch', 'rds-aurora', or 'rds-postgres'"
exit 1
;;
esac
echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
QUERY="SELECT version();"
if [[ "${PLATFORM}" = "neon"* ]]; then
QUERY="${QUERY} SHOW neon.tenant_id; SHOW neon.timeline_id;"
fi
psql ${CONNSTR} -c "${QUERY}"
psql ${CONNSTR} -c "SELECT version();"
- name: Set database options
if: matrix.platform == 'neon-captest-prefetch'
run: |
DB_NAME=$(psql ${BENCHMARK_CONNSTR} --no-align --quiet -t -c "SELECT current_database()")
psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET enable_seqscan_prefetch=on"
psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET effective_io_concurrency=32"
psql ${BENCHMARK_CONNSTR} -c "ALTER DATABASE ${DB_NAME} SET maintenance_io_concurrency=32"
env:
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
- name: Run user examples
uses: ./.github/actions/run-python-test-set
@@ -596,14 +580,17 @@ jobs:
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
- name: Create Allure report
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
if: success() || failure()
uses: ./.github/actions/allure-report
with:
action: generate
build_type: ${{ env.BUILD_TYPE }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@v1
with:
channel-id: "C033QLM5P7D" # dev-staging-stream
slack-message: "Periodic User example perf testing ${{ matrix.platform }}: ${{ job.status }}\n${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}"
slack-message: "Periodic TPC-H perf testing ${{ matrix.platform }}: ${{ job.status }}\n${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}"
env:
SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}

File diff suppressed because it is too large Load Diff

View File

@@ -3,8 +3,7 @@ name: Check neon with extra platform builds
on:
push:
branches:
- main
pull_request:
- main
defaults:
run:
@@ -12,7 +11,7 @@ defaults:
concurrency:
# Allow only one workflow per any non-`main` branch.
group: ${{ github.workflow }}-${{ github.ref_name }}-${{ github.ref_name == 'main' && github.sha || 'anysha' }}
group: ${{ github.workflow }}-${{ github.ref }}-${{ github.ref == 'refs/heads/main' && github.sha || 'anysha' }}
cancel-in-progress: true
env:
@@ -21,7 +20,6 @@ env:
jobs:
check-macos-build:
if: github.ref_name == 'main' || contains(github.event.pull_request.labels.*.name, 'run-extra-build-macos')
timeout-minutes: 90
runs-on: macos-latest
@@ -38,7 +36,7 @@ jobs:
fetch-depth: 1
- name: Install macOS postgres dependencies
run: brew install flex bison openssl protobuf icu4c pkg-config
run: brew install flex bison openssl protobuf
- name: Set pg 14 revision for caching
id: pg_v14_rev
@@ -48,30 +46,19 @@ jobs:
id: pg_v15_rev
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v15) >> $GITHUB_OUTPUT
- name: Set pg 16 revision for caching
id: pg_v16_rev
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v16) >> $GITHUB_OUTPUT
- name: Cache postgres v14 build
id: cache_pg_14
uses: actions/cache@v3
with:
path: pg_install/v14
key: v1-${{ runner.os }}-${{ env.BUILD_TYPE }}-pg-${{ steps.pg_v14_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
key: v1-${{ runner.os }}-${{ matrix.build_type }}-pg-${{ steps.pg_v14_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Cache postgres v15 build
id: cache_pg_15
uses: actions/cache@v3
with:
path: pg_install/v15
key: v1-${{ runner.os }}-${{ env.BUILD_TYPE }}-pg-${{ steps.pg_v15_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Cache postgres v16 build
id: cache_pg_16
uses: actions/cache@v3
with:
path: pg_install/v16
key: v1-${{ runner.os }}-${{ env.BUILD_TYPE }}-pg-${{ steps.pg_v16_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
key: v1-${{ runner.os }}-${{ matrix.build_type }}-pg-${{ steps.pg_v15_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Set extra env for macOS
run: |
@@ -96,10 +83,6 @@ jobs:
if: steps.cache_pg_15.outputs.cache-hit != 'true'
run: make postgres-v15 -j$(nproc)
- name: Build postgres v16
if: steps.cache_pg_16.outputs.cache-hit != 'true'
run: make postgres-v16 -j$(nproc)
- name: Build neon extensions
run: make neon-pg-ext -j$(nproc)
@@ -110,16 +93,11 @@ jobs:
run: ./run_clippy.sh
gather-rust-build-stats:
if: github.ref_name == 'main' || contains(github.event.pull_request.labels.*.name, 'run-extra-build-stats')
runs-on: [ self-hosted, gen3, large ]
container:
image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
options: --init
timeout-minutes: 90
runs-on: ubuntu-latest
env:
BUILD_TYPE: release
# remove the cachepot wrapper and build without crate caches
RUSTC_WRAPPER: ""
# build with incremental compilation produce partial results
# so do not attempt to cache this build, also disable the incremental compilation
CARGO_INCREMENTAL: 0
@@ -131,6 +109,11 @@ jobs:
submodules: true
fetch-depth: 1
- name: Install Ubuntu postgres dependencies
run: |
sudo apt update
sudo apt install build-essential libreadline-dev zlib1g-dev flex bison libseccomp-dev libssl-dev protobuf-compiler
# Some of our rust modules use FFI and need those to be checked
- name: Get postgres headers
run: make postgres-headers -j$(nproc)
@@ -139,31 +122,7 @@ jobs:
run: cargo build --all --release --timings
- name: Upload the build stats
id: upload-stats
env:
BUCKET: neon-github-public-dev
SHA: ${{ github.event.pull_request.head.sha || github.sha }}
AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
run: |
REPORT_URL=https://${BUCKET}.s3.amazonaws.com/build-stats/${SHA}/${GITHUB_RUN_ID}/cargo-timing.html
aws s3 cp --only-show-errors ./target/cargo-timings/cargo-timing.html "s3://${BUCKET}/build-stats/${SHA}/${GITHUB_RUN_ID}/"
echo "report-url=${REPORT_URL}" >> $GITHUB_OUTPUT
- name: Publish build stats report
uses: actions/github-script@v6
env:
REPORT_URL: ${{ steps.upload-stats.outputs.report-url }}
SHA: ${{ github.event.pull_request.head.sha || github.sha }}
uses: actions/upload-artifact@v3
with:
script: |
const { REPORT_URL, SHA } = process.env
await github.rest.repos.createCommitStatus({
owner: context.repo.owner,
repo: context.repo.repo,
sha: `${SHA}`,
state: 'success',
target_url: `${REPORT_URL}`,
context: `Build stats (release)`,
})
name: neon-${{ runner.os }}-release-build-stats
path: ./target/cargo-timings/

View File

@@ -14,7 +14,7 @@ on:
concurrency:
# Allow only one workflow per any non-`main` branch.
group: ${{ github.workflow }}-${{ github.ref_name }}-${{ github.ref_name == 'main' && github.sha || 'anysha' }}
group: ${{ github.workflow }}-${{ github.ref }}-${{ github.ref == 'refs/heads/main' && github.sha || 'anysha' }}
cancel-in-progress: true
jobs:

View File

@@ -1,29 +0,0 @@
name: Notify Slack channel about upcoming release
concurrency:
group: ${{ github.workflow }}-${{ github.event.number }}
cancel-in-progress: true
on:
pull_request:
branches:
- release
types:
# Default types that triggers a workflow:
# - https://docs.github.com/en/actions/using-workflows/events-that-trigger-workflows#pull_request
- opened
- synchronize
- reopened
# Additional types that we want to handle:
- closed
jobs:
notify:
runs-on: [ ubuntu-latest ]
steps:
- uses: neondatabase/dev-actions/release-pr-notify@main
with:
slack-token: ${{ secrets.SLACK_BOT_TOKEN }}
slack-channel-id: ${{ vars.SLACK_UPCOMING_RELEASE_CHANNEL_ID || 'C05QQ9J1BRC' }} # if not set, then `#test-release-notifications`
github-token: ${{ secrets.GITHUB_TOKEN }}

View File

@@ -1,44 +0,0 @@
name: Create Release Branch
on:
schedule:
- cron: '0 7 * * 2'
workflow_dispatch:
jobs:
create_release_branch:
runs-on: [ ubuntu-latest ]
permissions:
contents: write # for `git push`
steps:
- name: Check out code
uses: actions/checkout@v4
with:
ref: main
- name: Get current date
id: date
run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_OUTPUT
- name: Create release branch
run: git checkout -b releases/${{ steps.date.outputs.date }}
- name: Push new branch
run: git push origin releases/${{ steps.date.outputs.date }}
- name: Create pull request into release
env:
GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
run: |
cat << EOF > body.md
## Release ${{ steps.date.outputs.date }}
**Please merge this PR using 'Create a merge commit'!**
EOF
gh pr create --title "Release ${{ steps.date.outputs.date }}" \
--body-file "body.md" \
--head "releases/${{ steps.date.outputs.date }}" \
--base "release"

4
.gitmodules vendored
View File

@@ -6,7 +6,3 @@
path = vendor/postgres-v15
url = https://github.com/neondatabase/postgres.git
branch = REL_15_STABLE_neon
[submodule "vendor/postgres-v16"]
path = vendor/postgres-v16
url = https://github.com/neondatabase/postgres.git
branch = REL_16_STABLE_neon

View File

@@ -1,4 +0,0 @@
# * `-A unknown_lints` do not warn about unknown lint suppressions
# that people with newer toolchains might use
# * `-D warnings` - fail on any warnings (`cargo` returns non-zero exit status)
export CLIPPY_COMMON_ARGS="--locked --workspace --all-targets -- -A unknown_lints -D warnings"

View File

@@ -1,12 +1,11 @@
/compute_tools/ @neondatabase/control-plane @neondatabase/compute
/compute_tools/ @neondatabase/control-plane
/control_plane/ @neondatabase/compute @neondatabase/storage
/libs/pageserver_api/ @neondatabase/compute @neondatabase/storage
/libs/postgres_ffi/ @neondatabase/compute
/libs/remote_storage/ @neondatabase/storage
/libs/safekeeper_api/ @neondatabase/safekeepers
/libs/vm_monitor/ @neondatabase/autoscaling @neondatabase/compute
/pageserver/ @neondatabase/compute @neondatabase/storage
/libs/postgres_ffi/ @neondatabase/compute
/libs/remote_storage/ @neondatabase/storage
/libs/safekeeper_api/ @neondatabase/safekeepers
/pageserver/ @neondatabase/compute @neondatabase/storage
/pgxn/ @neondatabase/compute
/proxy/ @neondatabase/proxy
/proxy/ @neondatabase/control-plane
/safekeeper/ @neondatabase/safekeepers
/vendor/ @neondatabase/compute

View File

@@ -2,7 +2,7 @@
Howdy! Usual good software engineering practices apply. Write
tests. Write comments. Follow standard Rust coding practices where
possible. Use `cargo fmt` and `cargo clippy` to tidy up formatting.
possible. Use 'cargo fmt' and 'clippy' to tidy up formatting.
There are soft spots in the code, which could use cleanup,
refactoring, additional comments, and so forth. Let's try to raise the
@@ -27,28 +27,3 @@ your patch's fault. Help to fix the root cause if something else has
broken the CI, before pushing.
*Happy Hacking!*
# How to run a CI pipeline on Pull Requests from external contributors
_An instruction for maintainers_
## TL;DR:
- Review the PR
- If and only if it looks **safe** (i.e. it doesn't contain any malicious code which could expose secrets or harm the CI), then:
- Press the "Approve and run" button in GitHub UI
- Add the `approved-for-ci-run` label to the PR
Repeat all steps after any change to the PR.
- When the changes are ready to get merged — merge the original PR (not the internal one)
## Longer version:
GitHub Actions triggered by the `pull_request` event don't share repository secrets with the forks (for security reasons).
So, passing the CI pipeline on Pull Requests from external contributors is impossible.
We're using the following approach to make it work:
- After the review, assign the `approved-for-ci-run` label to the PR if changes look safe
- A GitHub Action will create an internal branch and a new PR with the same changes (for example, for a PR `#1234`, it'll be a branch `ci-run/pr-1234`)
- Because the PR is created from the internal branch, it is able to access repository secrets (that's why it's crucial to make sure that the PR doesn't contain any malicious code that could expose our secrets or intentionally harm the CI)
- The label gets removed automatically, so to run CI again with new changes, the label should be added again (after the review)
For details see [`approved-for-ci-run.yml`](.github/workflows/approved-for-ci-run.yml)

2738
Cargo.lock generated

File diff suppressed because it is too large Load Diff

View File

@@ -1,31 +1,13 @@
[workspace]
resolver = "2"
members = [
"compute_tools",
"control_plane",
"pageserver",
"pageserver/ctl",
"proxy",
"safekeeper",
"storage_broker",
"s3_scrubber",
"workspace_hack",
"trace",
"libs/compute_api",
"libs/pageserver_api",
"libs/postgres_ffi",
"libs/safekeeper_api",
"libs/utils",
"libs/consumption_metrics",
"libs/postgres_backend",
"libs/pq_proto",
"libs/tenant_size_model",
"libs/metrics",
"libs/postgres_connection",
"libs/remote_storage",
"libs/tracing-utils",
"libs/postgres_ffi/wal_craft",
"libs/vm_monitor",
"libs/*",
]
[workspace.package]
@@ -35,34 +17,26 @@ license = "Apache-2.0"
## All dependency versions, used in the project
[workspace.dependencies]
anyhow = { version = "1.0", features = ["backtrace"] }
async-compression = { version = "0.4.0", features = ["tokio", "gzip"] }
flate2 = "1.0.26"
async-stream = "0.3"
async-trait = "0.1"
aws-config = { version = "0.56", default-features = false, features=["rustls"] }
aws-sdk-s3 = "0.29"
aws-smithy-http = "0.56"
aws-credential-types = "0.56"
aws-types = "0.56"
axum = { version = "0.6.20", features = ["ws"] }
atty = "0.2.14"
aws-config = { version = "0.51.0", default-features = false, features=["rustls"] }
aws-sdk-s3 = "0.21.0"
aws-smithy-http = "0.51.0"
aws-types = "0.51.0"
base64 = "0.13.0"
bincode = "1.3"
bindgen = "0.65"
bindgen = "0.61"
bstr = "1.0"
byteorder = "1.4"
bytes = "1.0"
cfg-if = "1.0.0"
chrono = { version = "0.4", default-features = false, features = ["clock"] }
clap = { version = "4.0", features = ["derive"] }
clap = "4.0"
close_fds = "0.3.2"
comfy-table = "6.1"
const_format = "0.2"
crc32c = "0.6"
crossbeam-utils = "0.8.5"
dashmap = "5.5.0"
either = "1.8"
enum-map = "2.4.2"
enumset = "1.0.12"
fail = "0.5.0"
fs2 = "0.4.3"
futures = "0.3"
@@ -70,105 +44,80 @@ futures-core = "0.3"
futures-util = "0.3"
git-version = "0.3"
hashbrown = "0.13"
hashlink = "0.8.1"
hex = "0.4"
hex-literal = "0.4"
hex-literal = "0.3"
hmac = "0.12.1"
hostname = "0.3.1"
humantime = "2.1"
humantime-serde = "1.1.1"
hyper = "0.14"
hyper-tungstenite = "0.11"
inotify = "0.10.2"
hyper-tungstenite = "0.9"
itertools = "0.10"
jsonwebtoken = "8"
libc = "0.2"
md5 = "0.7.0"
memoffset = "0.8"
native-tls = "0.2"
nix = "0.26"
notify = "5.0.0"
num_cpus = "1.15"
num-traits = "0.2.15"
once_cell = "1.13"
opentelemetry = "0.19.0"
opentelemetry-otlp = { version = "0.12.0", default_features=false, features = ["http-proto", "trace", "http", "reqwest-client"] }
opentelemetry-semantic-conventions = "0.11.0"
parking_lot = "0.12"
pbkdf2 = { version = "0.12.1", features = ["simple", "std"] }
pin-project-lite = "0.2"
prometheus = {version = "0.13", default_features=false, features = ["process"]} # removes protobuf dependency
prost = "0.11"
rand = "0.8"
regex = "1.4"
reqwest = { version = "0.11", default-features = false, features = ["rustls-tls"] }
reqwest-tracing = { version = "0.4.0", features = ["opentelemetry_0_19"] }
reqwest-middleware = "0.2.0"
reqwest-retry = "0.2.2"
routerify = "3"
rpds = "0.13"
rustc-hash = "1.1.0"
rustls = "0.21"
rpds = "0.12.0"
rustls = "0.20"
rustls-pemfile = "1"
rustls-split = "0.3"
scopeguard = "1.1"
sysinfo = "0.29.2"
sentry = { version = "0.31", default-features = false, features = ["backtrace", "contexts", "panic", "rustls", "reqwest" ] }
sentry = { version = "0.29", default-features = false, features = ["backtrace", "contexts", "panic", "rustls", "reqwest" ] }
serde = { version = "1.0", features = ["derive"] }
serde_json = "1"
serde_with = "2.0"
sha2 = "0.10.2"
signal-hook = "0.3"
smallvec = "1.11"
socket2 = "0.5"
socket2 = "0.4.4"
strum = "0.24"
strum_macros = "0.24"
svg_fmt = "0.4.1"
sync_wrapper = "0.1.2"
tar = "0.4"
test-context = "0.1"
thiserror = "1.0"
tls-listener = { version = "0.7", features = ["rustls", "hyper-h1"] }
tls-listener = { version = "0.6", features = ["rustls", "hyper-h1"] }
tokio = { version = "1.17", features = ["macros"] }
tokio-io-timeout = "1.2.0"
tokio-postgres-rustls = "0.10.0"
tokio-rustls = "0.24"
tokio-postgres-rustls = "0.9.0"
tokio-rustls = "0.23"
tokio-stream = "0.1"
tokio-tar = "0.3"
tokio-util = { version = "0.7", features = ["io"] }
toml = "0.7"
toml_edit = "0.19"
tonic = {version = "0.9", features = ["tls", "tls-roots"]}
toml = "0.5"
toml_edit = { version = "0.17", features = ["easy"] }
tonic = {version = "0.8", features = ["tls", "tls-roots"]}
tracing = "0.1"
tracing-error = "0.2.0"
tracing-opentelemetry = "0.19.0"
tracing-subscriber = { version = "0.3", default_features = false, features = ["smallvec", "fmt", "tracing-log", "std", "env-filter", "json"] }
tracing-subscriber = { version = "0.3", features = ["env-filter"] }
url = "2.2"
uuid = { version = "1.2", features = ["v4", "serde"] }
walkdir = "2.3.2"
webpki-roots = "0.25"
x509-parser = "0.15"
webpki-roots = "0.22.5"
x509-parser = "0.14"
## TODO replace this with tracing
env_logger = "0.10"
log = "0.4"
## Libraries from neondatabase/ git forks, ideally with changes to be upstreamed
postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="9011f7110db12b5e15afaf98f8ac834501d50ddc" }
postgres-native-tls = { git = "https://github.com/neondatabase/rust-postgres.git", rev="9011f7110db12b5e15afaf98f8ac834501d50ddc" }
postgres-protocol = { git = "https://github.com/neondatabase/rust-postgres.git", rev="9011f7110db12b5e15afaf98f8ac834501d50ddc" }
postgres-types = { git = "https://github.com/neondatabase/rust-postgres.git", rev="9011f7110db12b5e15afaf98f8ac834501d50ddc" }
tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="9011f7110db12b5e15afaf98f8ac834501d50ddc" }
## Other git libraries
heapless = { default-features=false, features=[], git = "https://github.com/japaric/heapless.git", rev = "644653bf3b831c6bb4963be2de24804acf5e5001" } # upstream release pending
postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e" }
postgres-protocol = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e" }
postgres-types = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e" }
tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e" }
tokio-tar = { git = "https://github.com/neondatabase/tokio-tar.git", rev="404df61437de0feef49ba2ccdbdd94eb8ad6e142" }
## Local libraries
compute_api = { version = "0.1", path = "./libs/compute_api/" }
consumption_metrics = { version = "0.1", path = "./libs/consumption_metrics/" }
metrics = { version = "0.1", path = "./libs/metrics/" }
pageserver_api = { version = "0.1", path = "./libs/pageserver_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/" }
pq_proto = { version = "0.1", path = "./libs/pq_proto/" }
@@ -176,25 +125,22 @@ remote_storage = { version = "0.1", path = "./libs/remote_storage/" }
safekeeper_api = { version = "0.1", path = "./libs/safekeeper_api" }
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.
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/" }
## Common library dependency
workspace_hack = { version = "0.1", path = "./workspace_hack/" }
## Build dependencies
criterion = "0.5.1"
rcgen = "0.11"
rstest = "0.18"
tempfile = "3.4"
tonic-build = "0.9"
[patch.crates-io]
criterion = "0.4"
rcgen = "0.10"
rstest = "0.16"
tempfile = "3.2"
tonic-build = "0.8"
# This is only needed for proxy's tests.
# TODO: we should probably fork `tokio-postgres-rustls` instead.
tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="9011f7110db12b5e15afaf98f8ac834501d50ddc" }
[patch.crates-io]
tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e" }
################# Binary contents sections

View File

@@ -2,7 +2,7 @@
### The image itself is mainly used as a container for the binaries and for starting e2e tests with custom parameters.
### By default, the binaries inside the image have some mock parameters and can start, but are not intended to be used
### inside this image in the real deployments.
ARG REPOSITORY=neondatabase
ARG REPOSITORY=369495373322.dkr.ecr.eu-central-1.amazonaws.com
ARG IMAGE=rust
ARG TAG=pinned
@@ -12,7 +12,6 @@ WORKDIR /home/nonroot
COPY --chown=nonroot vendor/postgres-v14 vendor/postgres-v14
COPY --chown=nonroot vendor/postgres-v15 vendor/postgres-v15
COPY --chown=nonroot vendor/postgres-v16 vendor/postgres-v16
COPY --chown=nonroot pgxn pgxn
COPY --chown=nonroot Makefile Makefile
COPY --chown=nonroot scripts/ninstall.sh scripts/ninstall.sh
@@ -40,21 +39,12 @@ ARG CACHEPOT_BUCKET=neon-github-dev
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 --chown=nonroot . .
COPY . .
# Show build caching stats to check if it was used in the end.
# Has to be the part of the same RUN since cachepot daemon is killed in the end of this RUN, losing the compilation stats.
RUN set -e \
&& mold -run cargo build \
--bin pg_sni_router \
--bin pageserver \
--bin pagectl \
--bin safekeeper \
--bin storage_broker \
--bin proxy \
--bin neon_local \
--locked --release \
&& mold -run cargo build --bin pageserver --bin pageserver_binutils --bin draw_timeline_dir --bin safekeeper --bin storage_broker --bin proxy --locked --release \
&& cachepot -s
# Build final image
@@ -67,24 +57,21 @@ RUN set -e \
&& apt install -y \
libreadline-dev \
libseccomp-dev \
libicu67 \
openssl \
ca-certificates \
&& rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* \
&& useradd -d /data neon \
&& chown -R neon:neon /data
COPY --from=build --chown=neon:neon /home/nonroot/target/release/pg_sni_router /usr/local/bin
COPY --from=build --chown=neon:neon /home/nonroot/target/release/pageserver /usr/local/bin
COPY --from=build --chown=neon:neon /home/nonroot/target/release/pagectl /usr/local/bin
COPY --from=build --chown=neon:neon /home/nonroot/target/release/pageserver_binutils /usr/local/bin
COPY --from=build --chown=neon:neon /home/nonroot/target/release/draw_timeline_dir /usr/local/bin
COPY --from=build --chown=neon:neon /home/nonroot/target/release/safekeeper /usr/local/bin
COPY --from=build --chown=neon:neon /home/nonroot/target/release/storage_broker /usr/local/bin
COPY --from=build --chown=neon:neon /home/nonroot/target/release/proxy /usr/local/bin
COPY --from=build --chown=neon:neon /home/nonroot/target/release/neon_local /usr/local/bin
COPY --from=pg-build /home/nonroot/pg_install/v14 /usr/local/v14/
COPY --from=pg-build /home/nonroot/pg_install/v15 /usr/local/v15/
COPY --from=pg-build /home/nonroot/pg_install/v16 /usr/local/v16/
COPY --from=pg-build /home/nonroot/postgres_install.tar.gz /data/
# By default, pageserver uses `.neon/` working directory in WORKDIR, so create one and fill it with the dummy config.

View File

@@ -1,932 +0,0 @@
ARG PG_VERSION
ARG REPOSITORY=neondatabase
ARG IMAGE=rust
ARG TAG=pinned
ARG BUILD_TAG
#########################################################################################
#
# Layer "build-deps"
#
#########################################################################################
FROM debian:bullseye-slim AS build-deps
RUN apt update && \
apt install -y git autoconf automake libtool build-essential bison flex libreadline-dev \
zlib1g-dev libxml2-dev libcurl4-openssl-dev libossp-uuid-dev wget pkg-config libssl-dev \
libicu-dev libxslt1-dev liblz4-dev libzstd-dev zstd
#########################################################################################
#
# Layer "pg-build"
# Build Postgres from the neon postgres repository.
#
#########################################################################################
FROM build-deps AS pg-build
ARG PG_VERSION
COPY vendor/postgres-${PG_VERSION} postgres
RUN cd postgres && \
export CONFIGURE_CMD="./configure CFLAGS='-O2 -g3' --enable-debug --with-openssl --with-uuid=ossp \
--with-icu --with-libxml --with-libxslt --with-lz4" && \
if [ "${PG_VERSION}" != "v14" ]; then \
# zstd is available only from PG15
export CONFIGURE_CMD="${CONFIGURE_CMD} --with-zstd"; \
fi && \
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/bloom.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/earthdistance.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/insert_username.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/intagg.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/moddatetime.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/pg_stat_statements.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/pgrowlocks.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/pgstattuple.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/refint.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/xml2.control
#########################################################################################
#
# Layer "postgis-build"
# Build PostGIS from the upstream PostGIS mirror.
#
#########################################################################################
FROM build-deps AS postgis-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN apt update && \
apt install -y cmake gdal-bin libboost-dev libboost-thread-dev libboost-filesystem-dev \
libboost-system-dev libboost-iostreams-dev libboost-program-options-dev libboost-timer-dev \
libcgal-dev libgdal-dev libgmp-dev libmpfr-dev libopenscenegraph-dev libprotobuf-c-dev \
protobuf-c-compiler xsltproc
# SFCGAL > 1.3 requires CGAL > 5.2, Bullseye's libcgal-dev is 5.2
RUN wget https://gitlab.com/Oslandia/SFCGAL/-/archive/v1.3.10/SFCGAL-v1.3.10.tar.gz -O SFCGAL.tar.gz && \
echo "4e39b3b2adada6254a7bdba6d297bb28e1a9835a9f879b74f37e2dab70203232 SFCGAL.tar.gz" | sha256sum --check && \
mkdir sfcgal-src && cd sfcgal-src && tar xvzf ../SFCGAL.tar.gz --strip-components=1 -C . && \
cmake -DCMAKE_BUILD_TYPE=Release . && make -j $(getconf _NPROCESSORS_ONLN) && \
DESTDIR=/sfcgal make install -j $(getconf _NPROCESSORS_ONLN) && \
make clean && cp -R /sfcgal/* /
ENV PATH "/usr/local/pgsql/bin:$PATH"
RUN wget https://download.osgeo.org/postgis/source/postgis-3.3.3.tar.gz -O postgis.tar.gz && \
echo "74eb356e3f85f14233791013360881b6748f78081cc688ff9d6f0f673a762d13 postgis.tar.gz" | sha256sum --check && \
mkdir postgis-src && cd postgis-src && tar xvzf ../postgis.tar.gz --strip-components=1 -C . && \
find /usr/local/pgsql -type f | sed 's|^/usr/local/pgsql/||' > /before.txt &&\
./autogen.sh && \
./configure --with-sfcgal=/usr/local/bin/sfcgal-config && \
make -j $(getconf _NPROCESSORS_ONLN) install && \
cd extensions/postgis && \
make clean && \
make -j $(getconf _NPROCESSORS_ONLN) install && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_raster.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_sfcgal.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_tiger_geocoder.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_topology.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/address_standardizer.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/address_standardizer_data_us.control && \
mkdir -p /extensions/postgis && \
cp /usr/local/pgsql/share/extension/postgis.control /extensions/postgis && \
cp /usr/local/pgsql/share/extension/postgis_raster.control /extensions/postgis && \
cp /usr/local/pgsql/share/extension/postgis_sfcgal.control /extensions/postgis && \
cp /usr/local/pgsql/share/extension/postgis_tiger_geocoder.control /extensions/postgis && \
cp /usr/local/pgsql/share/extension/postgis_topology.control /extensions/postgis && \
cp /usr/local/pgsql/share/extension/address_standardizer.control /extensions/postgis && \
cp /usr/local/pgsql/share/extension/address_standardizer_data_us.control /extensions/postgis
RUN wget https://github.com/pgRouting/pgrouting/archive/v3.4.2.tar.gz -O pgrouting.tar.gz && \
echo "cac297c07d34460887c4f3b522b35c470138760fe358e351ad1db4edb6ee306e pgrouting.tar.gz" | sha256sum --check && \
mkdir pgrouting-src && cd pgrouting-src && tar xvzf ../pgrouting.tar.gz --strip-components=1 -C . && \
mkdir build && cd build && \
cmake -DCMAKE_BUILD_TYPE=Release .. && \
make -j $(getconf _NPROCESSORS_ONLN) && \
make -j $(getconf _NPROCESSORS_ONLN) install && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/pgrouting.control && \
find /usr/local/pgsql -type f | sed 's|^/usr/local/pgsql/||' > /after.txt &&\
cp /usr/local/pgsql/share/extension/pgrouting.control /extensions/postgis && \
sort -o /before.txt /before.txt && sort -o /after.txt /after.txt && \
comm -13 /before.txt /after.txt | tar --directory=/usr/local/pgsql --zstd -cf /extensions/postgis.tar.zst -T -
#########################################################################################
#
# Layer "plv8-build"
# Build plv8
#
#########################################################################################
FROM build-deps AS plv8-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN apt update && \
apt install -y ninja-build python3-dev libncurses5 binutils clang
RUN case "${PG_VERSION}" in \
"v14" | "v15") \
export PLV8_VERSION=3.1.5 \
export PLV8_CHECKSUM=1e108d5df639e4c189e1c5bdfa2432a521c126ca89e7e5a969d46899ca7bf106 \
;; \
"v16") \
export PLV8_VERSION=3.1.8 \
export PLV8_CHECKSUM=92b10c7db39afdae97ff748c9ec54713826af222c459084ad002571b79eb3f49 \
;; \
*) \
echo "Export the valid PG_VERSION variable" && exit 1 \
;; \
esac && \
wget https://github.com/plv8/plv8/archive/refs/tags/v${PLV8_VERSION}.tar.gz -O plv8.tar.gz && \
echo "${PLV8_CHECKSUM} plv8.tar.gz" | sha256sum --check && \
mkdir plv8-src && cd plv8-src && tar xvzf ../plv8.tar.gz --strip-components=1 -C . && \
export PATH="/usr/local/pgsql/bin:$PATH" && \
make DOCKER=1 -j $(getconf _NPROCESSORS_ONLN) install && \
rm -rf /plv8-* && \
find /usr/local/pgsql/ -name "plv8-*.so" | xargs strip && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/plv8.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/plcoffee.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/plls.control
#########################################################################################
#
# Layer "h3-pg-build"
# Build h3_pg
#
#########################################################################################
FROM build-deps AS h3-pg-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN case "$(uname -m)" in \
"x86_64") \
export CMAKE_CHECKSUM=739d372726cb23129d57a539ce1432453448816e345e1545f6127296926b6754 \
;; \
"aarch64") \
export CMAKE_CHECKSUM=281b42627c9a1beed03e29706574d04c6c53fae4994472e90985ef018dd29c02 \
;; \
*) \
echo "Unsupported architecture '$(uname -m)'. Supported are x86_64 and aarch64" && exit 1 \
;; \
esac && \
wget https://github.com/Kitware/CMake/releases/download/v3.24.2/cmake-3.24.2-linux-$(uname -m).sh \
-q -O /tmp/cmake-install.sh \
&& echo "${CMAKE_CHECKSUM} /tmp/cmake-install.sh" | sha256sum --check \
&& chmod u+x /tmp/cmake-install.sh \
&& /tmp/cmake-install.sh --skip-license --prefix=/usr/local/ \
&& rm /tmp/cmake-install.sh
RUN wget https://github.com/uber/h3/archive/refs/tags/v4.1.0.tar.gz -O h3.tar.gz && \
echo "ec99f1f5974846bde64f4513cf8d2ea1b8d172d2218ab41803bf6a63532272bc h3.tar.gz" | sha256sum --check && \
mkdir h3-src && cd h3-src && tar xvzf ../h3.tar.gz --strip-components=1 -C . && \
mkdir build && cd build && \
cmake .. -DCMAKE_BUILD_TYPE=Release && \
make -j $(getconf _NPROCESSORS_ONLN) && \
DESTDIR=/h3 make install && \
cp -R /h3/usr / && \
rm -rf build
RUN wget https://github.com/zachasme/h3-pg/archive/refs/tags/v4.1.3.tar.gz -O h3-pg.tar.gz && \
echo "5c17f09a820859ffe949f847bebf1be98511fb8f1bd86f94932512c00479e324 h3-pg.tar.gz" | sha256sum --check && \
mkdir h3-pg-src && cd h3-pg-src && tar xvzf ../h3-pg.tar.gz --strip-components=1 -C . && \
export PATH="/usr/local/pgsql/bin:$PATH" && \
make -j $(getconf _NPROCESSORS_ONLN) && \
make -j $(getconf _NPROCESSORS_ONLN) install && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/h3.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/h3_postgis.control
#########################################################################################
#
# Layer "unit-pg-build"
# compile unit extension
#
#########################################################################################
FROM build-deps AS unit-pg-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN wget https://github.com/df7cb/postgresql-unit/archive/refs/tags/7.7.tar.gz -O postgresql-unit.tar.gz && \
echo "411d05beeb97e5a4abf17572bfcfbb5a68d98d1018918feff995f6ee3bb03e79 postgresql-unit.tar.gz" | sha256sum --check && \
mkdir postgresql-unit-src && cd postgresql-unit-src && tar xvzf ../postgresql-unit.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
# unit extension's "create extension" script relies on absolute install path to fill some reference tables.
# We move the extension from '/usr/local/pgsql/' to '/usr/local/' after it is build. So we need to adjust the path.
# This one-liner removes pgsql/ part of the path.
# NOTE: Other extensions that rely on MODULEDIR variable after building phase will need the same fix.
find /usr/local/pgsql/share/extension/ -name "unit*.sql" -print0 | xargs -0 sed -i "s|pgsql/||g" && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/unit.control
#########################################################################################
#
# Layer "vector-pg-build"
# compile pgvector extension
#
#########################################################################################
FROM build-deps AS vector-pg-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN wget https://github.com/pgvector/pgvector/archive/refs/tags/v0.5.0.tar.gz -O pgvector.tar.gz && \
echo "d8aa3504b215467ca528525a6de12c3f85f9891b091ce0e5864dd8a9b757f77b pgvector.tar.gz" | sha256sum --check && \
mkdir pgvector-src && cd pgvector-src && tar xvzf ../pgvector.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/vector.control
#########################################################################################
#
# Layer "pgjwt-pg-build"
# compile pgjwt extension
#
#########################################################################################
FROM build-deps AS pgjwt-pg-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
# 9742dab1b2f297ad3811120db7b21451bca2d3c9 made on 13/11/2021
RUN wget https://github.com/michelp/pgjwt/archive/9742dab1b2f297ad3811120db7b21451bca2d3c9.tar.gz -O pgjwt.tar.gz && \
echo "cfdefb15007286f67d3d45510f04a6a7a495004be5b3aecb12cda667e774203f pgjwt.tar.gz" | sha256sum --check && \
mkdir pgjwt-src && cd pgjwt-src && tar xvzf ../pgjwt.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/pgjwt.control
#########################################################################################
#
# Layer "hypopg-pg-build"
# compile hypopg extension
#
#########################################################################################
FROM build-deps AS hypopg-pg-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN wget https://github.com/HypoPG/hypopg/archive/refs/tags/1.4.0.tar.gz -O hypopg.tar.gz && \
echo "0821011743083226fc9b813c1f2ef5897a91901b57b6bea85a78e466187c6819 hypopg.tar.gz" | sha256sum --check && \
mkdir hypopg-src && cd hypopg-src && tar xvzf ../hypopg.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/hypopg.control
#########################################################################################
#
# Layer "pg-hashids-pg-build"
# compile pg_hashids extension
#
#########################################################################################
FROM build-deps AS pg-hashids-pg-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN wget https://github.com/iCyberon/pg_hashids/archive/refs/tags/v1.2.1.tar.gz -O pg_hashids.tar.gz && \
echo "74576b992d9277c92196dd8d816baa2cc2d8046fe102f3dcd7f3c3febed6822a pg_hashids.tar.gz" | sha256sum --check && \
mkdir pg_hashids-src && cd pg_hashids-src && tar xvzf ../pg_hashids.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config USE_PGXS=1 && \
make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config USE_PGXS=1 && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/pg_hashids.control
#########################################################################################
#
# Layer "rum-pg-build"
# compile rum extension
#
#########################################################################################
FROM build-deps AS rum-pg-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN wget https://github.com/postgrespro/rum/archive/refs/tags/1.3.13.tar.gz -O rum.tar.gz && \
echo "6ab370532c965568df6210bd844ac6ba649f53055e48243525b0b7e5c4d69a7d rum.tar.gz" | sha256sum --check && \
mkdir rum-src && cd rum-src && tar xvzf ../rum.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config USE_PGXS=1 && \
make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config USE_PGXS=1 && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/rum.control
#########################################################################################
#
# Layer "pgtap-pg-build"
# compile pgTAP extension
#
#########################################################################################
FROM build-deps AS pgtap-pg-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN wget https://github.com/theory/pgtap/archive/refs/tags/v1.2.0.tar.gz -O pgtap.tar.gz && \
echo "9c7c3de67ea41638e14f06da5da57bac6f5bd03fea05c165a0ec862205a5c052 pgtap.tar.gz" | sha256sum --check && \
mkdir pgtap-src && cd pgtap-src && tar xvzf ../pgtap.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/pgtap.control
#########################################################################################
#
# Layer "ip4r-pg-build"
# compile ip4r extension
#
#########################################################################################
FROM build-deps AS ip4r-pg-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN wget https://github.com/RhodiumToad/ip4r/archive/refs/tags/2.4.2.tar.gz -O ip4r.tar.gz && \
echo "0f7b1f159974f49a47842a8ab6751aecca1ed1142b6d5e38d81b064b2ead1b4b ip4r.tar.gz" | sha256sum --check && \
mkdir ip4r-src && cd ip4r-src && tar xvzf ../ip4r.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/ip4r.control
#########################################################################################
#
# Layer "prefix-pg-build"
# compile Prefix extension
#
#########################################################################################
FROM build-deps AS prefix-pg-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN wget https://github.com/dimitri/prefix/archive/refs/tags/v1.2.10.tar.gz -O prefix.tar.gz && \
echo "4342f251432a5f6fb05b8597139d3ccde8dcf87e8ca1498e7ee931ca057a8575 prefix.tar.gz" | sha256sum --check && \
mkdir prefix-src && cd prefix-src && tar xvzf ../prefix.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/prefix.control
#########################################################################################
#
# Layer "hll-pg-build"
# compile hll extension
#
#########################################################################################
FROM build-deps AS hll-pg-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN wget https://github.com/citusdata/postgresql-hll/archive/refs/tags/v2.18.tar.gz -O hll.tar.gz && \
echo "e2f55a6f4c4ab95ee4f1b4a2b73280258c5136b161fe9d059559556079694f0e hll.tar.gz" | sha256sum --check && \
mkdir hll-src && cd hll-src && tar xvzf ../hll.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/hll.control
#########################################################################################
#
# Layer "plpgsql-check-pg-build"
# compile plpgsql_check extension
#
#########################################################################################
FROM build-deps AS plpgsql-check-pg-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN wget https://github.com/okbob/plpgsql_check/archive/refs/tags/v2.4.0.tar.gz -O plpgsql_check.tar.gz && \
echo "9ba58387a279b35a3bfa39ee611e5684e6cddb2ba046ddb2c5190b3bd2ca254a plpgsql_check.tar.gz" | sha256sum --check && \
mkdir plpgsql_check-src && cd plpgsql_check-src && tar xvzf ../plpgsql_check.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) PG_CONFIG=/usr/local/pgsql/bin/pg_config USE_PGXS=1 && \
make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config USE_PGXS=1 && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/plpgsql_check.control
#########################################################################################
#
# Layer "timescaledb-pg-build"
# compile timescaledb extension
#
#########################################################################################
FROM build-deps AS timescaledb-pg-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
ARG PG_VERSION
ENV PATH "/usr/local/pgsql/bin:$PATH"
RUN case "${PG_VERSION}" in \
"v14" | "v15") \
export TIMESCALEDB_VERSION=2.10.1 \
export TIMESCALEDB_CHECKSUM=6fca72a6ed0f6d32d2b3523951ede73dc5f9b0077b38450a029a5f411fdb8c73 \
;; \
*) \
echo "TimescaleDB not supported on this PostgreSQL version. See https://github.com/timescale/timescaledb/issues/5752" && exit 0;; \
esac && \
apt-get update && \
apt-get install -y cmake && \
wget https://github.com/timescale/timescaledb/archive/refs/tags/${TIMESCALEDB_VERSION}.tar.gz -O timescaledb.tar.gz && \
echo "${TIMESCALEDB_CHECKSUM} timescaledb.tar.gz" | sha256sum --check && \
mkdir timescaledb-src && cd timescaledb-src && tar xvzf ../timescaledb.tar.gz --strip-components=1 -C . && \
./bootstrap -DSEND_TELEMETRY_DEFAULT:BOOL=OFF -DUSE_TELEMETRY:BOOL=OFF -DAPACHE_ONLY:BOOL=ON -DCMAKE_BUILD_TYPE=Release && \
cd build && \
make -j $(getconf _NPROCESSORS_ONLN) && \
make install -j $(getconf _NPROCESSORS_ONLN) && \
echo "trusted = true" >> /usr/local/pgsql/share/extension/timescaledb.control
#########################################################################################
#
# Layer "pg-hint-plan-pg-build"
# compile pg_hint_plan extension
#
#########################################################################################
FROM build-deps AS pg-hint-plan-pg-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
ARG PG_VERSION
ENV PATH "/usr/local/pgsql/bin:$PATH"
RUN case "${PG_VERSION}" in \
"v14") \
export PG_HINT_PLAN_VERSION=14_1_4_1 \
export PG_HINT_PLAN_CHECKSUM=c3501becf70ead27f70626bce80ea401ceac6a77e2083ee5f3ff1f1444ec1ad1 \
;; \
"v15") \
export PG_HINT_PLAN_VERSION=15_1_5_0 \
export PG_HINT_PLAN_CHECKSUM=564cbbf4820973ffece63fbf76e3c0af62c4ab23543142c7caaa682bc48918be \
;; \
"v16") \
export PG_HINT_PLAN_VERSION=16_1_6_0 \
export PG_HINT_PLAN_CHECKSUM=fc85a9212e7d2819d4ae4ac75817481101833c3cfa9f0fe1f980984e12347d00 \
;; \
*) \
echo "Export the valid PG_HINT_PLAN_VERSION variable" && exit 1 \
;; \
esac && \
wget https://github.com/ossc-db/pg_hint_plan/archive/refs/tags/REL${PG_HINT_PLAN_VERSION}.tar.gz -O pg_hint_plan.tar.gz && \
echo "${PG_HINT_PLAN_CHECKSUM} pg_hint_plan.tar.gz" | sha256sum --check && \
mkdir pg_hint_plan-src && cd pg_hint_plan-src && tar xvzf ../pg_hint_plan.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) && \
make install -j $(getconf _NPROCESSORS_ONLN) && \
echo "trusted = true" >> /usr/local/pgsql/share/extension/pg_hint_plan.control
#########################################################################################
#
# Layer "kq-imcx-pg-build"
# compile kq_imcx extension
#
#########################################################################################
FROM build-deps AS kq-imcx-pg-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
ENV PATH "/usr/local/pgsql/bin/:$PATH"
RUN apt-get update && \
apt-get install -y git libgtk2.0-dev libpq-dev libpam-dev libxslt-dev libkrb5-dev cmake && \
wget https://github.com/ketteq-neon/postgres-exts/archive/e0bd1a9d9313d7120c1b9c7bb15c48c0dede4c4e.tar.gz -O kq_imcx.tar.gz && \
echo "dc93a97ff32d152d32737ba7e196d9687041cda15e58ab31344c2f2de8855336 kq_imcx.tar.gz" | sha256sum --check && \
mkdir kq_imcx-src && cd kq_imcx-src && tar xvzf ../kq_imcx.tar.gz --strip-components=1 -C . && \
find /usr/local/pgsql -type f | sed 's|^/usr/local/pgsql/||' > /before.txt &&\
mkdir build && cd build && \
cmake -DCMAKE_BUILD_TYPE=Release .. && \
make -j $(getconf _NPROCESSORS_ONLN) && \
make -j $(getconf _NPROCESSORS_ONLN) install && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/kq_imcx.control && \
find /usr/local/pgsql -type f | sed 's|^/usr/local/pgsql/||' > /after.txt &&\
mkdir -p /extensions/kq_imcx && cp /usr/local/pgsql/share/extension/kq_imcx.control /extensions/kq_imcx && \
sort -o /before.txt /before.txt && sort -o /after.txt /after.txt && \
comm -13 /before.txt /after.txt | tar --directory=/usr/local/pgsql --zstd -cf /extensions/kq_imcx.tar.zst -T -
#########################################################################################
#
# Layer "pg-cron-pg-build"
# compile pg_cron extension
#
#########################################################################################
FROM build-deps AS pg-cron-pg-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
ENV PATH "/usr/local/pgsql/bin/:$PATH"
RUN wget https://github.com/citusdata/pg_cron/archive/refs/tags/v1.6.0.tar.gz -O pg_cron.tar.gz && \
echo "383a627867d730222c272bfd25cd5e151c578d73f696d32910c7db8c665cc7db pg_cron.tar.gz" | sha256sum --check && \
mkdir pg_cron-src && cd pg_cron-src && tar xvzf ../pg_cron.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) && \
make -j $(getconf _NPROCESSORS_ONLN) install && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/pg_cron.control
#########################################################################################
#
# Layer "rdkit-pg-build"
# compile rdkit extension
#
#########################################################################################
FROM build-deps AS rdkit-pg-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN apt-get update && \
apt-get install -y \
cmake \
libboost-iostreams1.74-dev \
libboost-regex1.74-dev \
libboost-serialization1.74-dev \
libboost-system1.74-dev \
libeigen3-dev \
libfreetype6-dev
ENV PATH "/usr/local/pgsql/bin/:/usr/local/pgsql/:$PATH"
RUN wget https://github.com/rdkit/rdkit/archive/refs/tags/Release_2023_03_3.tar.gz -O rdkit.tar.gz && \
echo "bdbf9a2e6988526bfeb8c56ce3cdfe2998d60ac289078e2215374288185e8c8d rdkit.tar.gz" | sha256sum --check && \
mkdir rdkit-src && cd rdkit-src && tar xvzf ../rdkit.tar.gz --strip-components=1 -C . && \
cmake \
-D RDK_BUILD_CAIRO_SUPPORT=OFF \
-D RDK_BUILD_INCHI_SUPPORT=ON \
-D RDK_BUILD_AVALON_SUPPORT=ON \
-D RDK_BUILD_PYTHON_WRAPPERS=OFF \
-D RDK_BUILD_DESCRIPTORS3D=OFF \
-D RDK_BUILD_FREESASA_SUPPORT=OFF \
-D RDK_BUILD_COORDGEN_SUPPORT=ON \
-D RDK_BUILD_MOLINTERCHANGE_SUPPORT=OFF \
-D RDK_BUILD_YAEHMOP_SUPPORT=OFF \
-D RDK_BUILD_STRUCTCHECKER_SUPPORT=OFF \
-D RDK_USE_URF=OFF \
-D RDK_BUILD_PGSQL=ON \
-D RDK_PGSQL_STATIC=ON \
-D PostgreSQL_CONFIG=pg_config \
-D PostgreSQL_INCLUDE_DIR=`pg_config --includedir` \
-D PostgreSQL_TYPE_INCLUDE_DIR=`pg_config --includedir-server` \
-D PostgreSQL_LIBRARY_DIR=`pg_config --libdir` \
-D RDK_INSTALL_INTREE=OFF \
-D CMAKE_BUILD_TYPE=Release \
. && \
make -j $(getconf _NPROCESSORS_ONLN) && \
make -j $(getconf _NPROCESSORS_ONLN) install && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/rdkit.control
#########################################################################################
#
# Layer "pg-uuidv7-pg-build"
# compile pg_uuidv7 extension
#
#########################################################################################
FROM build-deps AS pg-uuidv7-pg-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
ENV PATH "/usr/local/pgsql/bin/:$PATH"
RUN wget https://github.com/fboulnois/pg_uuidv7/archive/refs/tags/v1.0.1.tar.gz -O pg_uuidv7.tar.gz && \
echo "0d0759ab01b7fb23851ecffb0bce27822e1868a4a5819bfd276101c716637a7a pg_uuidv7.tar.gz" | sha256sum --check && \
mkdir pg_uuidv7-src && cd pg_uuidv7-src && tar xvzf ../pg_uuidv7.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) && \
make -j $(getconf _NPROCESSORS_ONLN) install && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/pg_uuidv7.control
#########################################################################################
#
# Layer "pg-roaringbitmap-pg-build"
# compile pg_roaringbitmap extension
#
#########################################################################################
FROM build-deps AS pg-roaringbitmap-pg-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
ENV PATH "/usr/local/pgsql/bin/:$PATH"
RUN wget https://github.com/ChenHuajun/pg_roaringbitmap/archive/refs/tags/v0.5.4.tar.gz -O pg_roaringbitmap.tar.gz && \
echo "b75201efcb1c2d1b014ec4ae6a22769cc7a224e6e406a587f5784a37b6b5a2aa pg_roaringbitmap.tar.gz" | sha256sum --check && \
mkdir pg_roaringbitmap-src && cd pg_roaringbitmap-src && tar xvzf ../pg_roaringbitmap.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) && \
make -j $(getconf _NPROCESSORS_ONLN) install && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/roaringbitmap.control
#########################################################################################
#
# Layer "pg-embedding-pg-build"
# compile pg_embedding extension
#
#########################################################################################
FROM build-deps AS pg-embedding-pg-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
ENV PATH "/usr/local/pgsql/bin/:$PATH"
RUN case "${PG_VERSION}" in \
"v14" | "v15") \
export PG_EMBEDDING_VERSION=0.3.5 \
export PG_EMBEDDING_CHECKSUM=0e95b27b8b6196e2cf0a0c9ec143fe2219b82e54c5bb4ee064e76398cbe69ae9 \
;; \
*) \
echo "pg_embedding not supported on this PostgreSQL version. Use pgvector instead." && exit 0;; \
esac && \
wget https://github.com/neondatabase/pg_embedding/archive/refs/tags/${PG_EMBEDDING_VERSION}.tar.gz -O pg_embedding.tar.gz && \
echo "${PG_EMBEDDING_CHECKSUM} pg_embedding.tar.gz" | sha256sum --check && \
mkdir pg_embedding-src && cd pg_embedding-src && tar xvzf ../pg_embedding.tar.gz --strip-components=1 -C . && \
make -j $(getconf _NPROCESSORS_ONLN) && \
make -j $(getconf _NPROCESSORS_ONLN) install
#########################################################################################
#
# Layer "pg-anon-pg-build"
# compile anon extension
#
#########################################################################################
FROM build-deps AS pg-anon-pg-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
ENV PATH "/usr/local/pgsql/bin/:$PATH"
RUN wget https://gitlab.com/dalibo/postgresql_anonymizer/-/archive/1.1.0/postgresql_anonymizer-1.1.0.tar.gz -O pg_anon.tar.gz && \
echo "08b09d2ff9b962f96c60db7e6f8e79cf7253eb8772516998fc35ece08633d3ad pg_anon.tar.gz" | sha256sum --check && \
mkdir pg_anon-src && cd pg_anon-src && tar xvzf ../pg_anon.tar.gz --strip-components=1 -C . && \
find /usr/local/pgsql -type f | sed 's|^/usr/local/pgsql/||' > /before.txt &&\
make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/anon.control && \
find /usr/local/pgsql -type f | sed 's|^/usr/local/pgsql/||' > /after.txt &&\
mkdir -p /extensions/anon && cp /usr/local/pgsql/share/extension/anon.control /extensions/anon && \
sort -o /before.txt /before.txt && sort -o /after.txt /after.txt && \
comm -13 /before.txt /after.txt | tar --directory=/usr/local/pgsql --zstd -cf /extensions/anon.tar.zst -T -
#########################################################################################
#
# Layer "rust extensions"
# This layer is used to build `pgx` deps
#
# FIXME: This needs to be updated to latest version of 'pgrx' (it was renamed from
# 'pgx' to 'pgrx') for PostgreSQL 16. And that in turn requires bumping the pgx
# dependency on all the rust extension that depend on it, too.
#
#########################################################################################
FROM build-deps AS rust-extensions-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN apt-get update && \
apt-get install -y curl libclang-dev cmake && \
useradd -ms /bin/bash nonroot -b /home
ENV HOME=/home/nonroot
ENV PATH="/home/nonroot/.cargo/bin:/usr/local/pgsql/bin/:$PATH"
USER nonroot
WORKDIR /home/nonroot
ARG PG_VERSION
RUN case "${PG_VERSION}" in \
"v14" | "v15") \
;; \
"v16") \
echo "TODO: Not yet supported for PostgreSQL 16. Need to update pgrx dependencies" && exit 0 \
;; \
*) \
echo "unexpected PostgreSQL version ${PG_VERSION}" && exit 1 \
;; \
esac && \
curl -sSO https://static.rust-lang.org/rustup/dist/$(uname -m)-unknown-linux-gnu/rustup-init && \
chmod +x rustup-init && \
./rustup-init -y --no-modify-path --profile minimal --default-toolchain stable && \
rm rustup-init && \
cargo install --locked --version 0.7.3 cargo-pgx && \
/bin/bash -c 'cargo pgx init --pg${PG_VERSION:1}=/usr/local/pgsql/bin/pg_config'
USER root
#########################################################################################
#
# Layer "pg-jsonschema-pg-build"
# Compile "pg_jsonschema" extension
#
#########################################################################################
FROM rust-extensions-build AS pg-jsonschema-pg-build
ARG PG_VERSION
# caeab60d70b2fd3ae421ec66466a3abbb37b7ee6 made on 06/03/2023
# there is no release tag yet, but we need it due to the superuser fix in the control file, switch to git tag after release >= 0.1.5
RUN case "${PG_VERSION}" in \
"v14" | "v15") \
;; \
"v16") \
echo "TODO: Not yet supported for PostgreSQL 16. Need to update pgrx dependencies" && exit 0 \
;; \
*) \
echo "unexpected PostgreSQL version \"${PG_VERSION}\"" && exit 1 \
;; \
esac && \
wget https://github.com/supabase/pg_jsonschema/archive/caeab60d70b2fd3ae421ec66466a3abbb37b7ee6.tar.gz -O pg_jsonschema.tar.gz && \
echo "54129ce2e7ee7a585648dbb4cef6d73f795d94fe72f248ac01119992518469a4 pg_jsonschema.tar.gz" | sha256sum --check && \
mkdir pg_jsonschema-src && cd pg_jsonschema-src && tar xvzf ../pg_jsonschema.tar.gz --strip-components=1 -C . && \
sed -i 's/pgx = "0.7.1"/pgx = { version = "0.7.3", features = [ "unsafe-postgres" ] }/g' Cargo.toml && \
cargo pgx install --release && \
echo "trusted = true" >> /usr/local/pgsql/share/extension/pg_jsonschema.control
#########################################################################################
#
# Layer "pg-graphql-pg-build"
# Compile "pg_graphql" extension
#
#########################################################################################
FROM rust-extensions-build AS pg-graphql-pg-build
ARG PG_VERSION
# b4988843647450a153439be367168ed09971af85 made on 22/02/2023 (from remove-pgx-contrib-spiext branch)
# Currently pgx version bump to >= 0.7.2 causes "call to unsafe function" compliation errors in
# pgx-contrib-spiext. There is a branch that removes that dependency, so use it. It is on the
# same 1.1 version we've used before.
RUN case "${PG_VERSION}" in \
"v14" | "v15") \
;; \
"v16") \
echo "TODO: Not yet supported for PostgreSQL 16. Need to update pgrx dependencies" && exit 0 \
;; \
*) \
echo "unexpected PostgreSQL version" && exit 1 \
;; \
esac && \
wget https://github.com/yrashk/pg_graphql/archive/b4988843647450a153439be367168ed09971af85.tar.gz -O pg_graphql.tar.gz && \
echo "0c7b0e746441b2ec24187d0e03555faf935c2159e2839bddd14df6dafbc8c9bd pg_graphql.tar.gz" | sha256sum --check && \
mkdir pg_graphql-src && cd pg_graphql-src && tar xvzf ../pg_graphql.tar.gz --strip-components=1 -C . && \
sed -i 's/pgx = "~0.7.1"/pgx = { version = "0.7.3", features = [ "unsafe-postgres" ] }/g' Cargo.toml && \
sed -i 's/pgx-tests = "~0.7.1"/pgx-tests = "0.7.3"/g' Cargo.toml && \
cargo pgx install --release && \
# it's needed to enable extension because it uses untrusted C language
sed -i 's/superuser = false/superuser = true/g' /usr/local/pgsql/share/extension/pg_graphql.control && \
echo "trusted = true" >> /usr/local/pgsql/share/extension/pg_graphql.control
#########################################################################################
#
# Layer "pg-tiktoken-build"
# Compile "pg_tiktoken" extension
#
#########################################################################################
FROM rust-extensions-build AS pg-tiktoken-pg-build
ARG PG_VERSION
# 801f84f08c6881c8aa30f405fafbf00eec386a72 made on 10/03/2023
RUN case "${PG_VERSION}" in \
"v14" | "v15") \
;; \
"v16") \
echo "TODO: Not yet supported for PostgreSQL 16. Need to update pgrx dependencies" && exit 0 \
;; \
*) \
echo "unexpected PostgreSQL version" && exit 1 \
;; \
esac && \
wget https://github.com/kelvich/pg_tiktoken/archive/801f84f08c6881c8aa30f405fafbf00eec386a72.tar.gz -O pg_tiktoken.tar.gz && \
echo "52f60ac800993a49aa8c609961842b611b6b1949717b69ce2ec9117117e16e4a pg_tiktoken.tar.gz" | sha256sum --check && \
mkdir pg_tiktoken-src && cd pg_tiktoken-src && tar xvzf ../pg_tiktoken.tar.gz --strip-components=1 -C . && \
cargo pgx install --release && \
echo "trusted = true" >> /usr/local/pgsql/share/extension/pg_tiktoken.control
#########################################################################################
#
# Layer "pg-pgx-ulid-build"
# Compile "pgx_ulid" extension
#
#########################################################################################
FROM rust-extensions-build AS pg-pgx-ulid-build
ARG PG_VERSION
RUN case "${PG_VERSION}" in \
"v14" | "v15") \
;; \
"v16") \
echo "TODO: Not yet supported for PostgreSQL 16. Need to update pgrx dependencies" && exit 0 \
;; \
*) \
echo "unexpected PostgreSQL version" && exit 1 \
;; \
esac && \
wget https://github.com/pksunkara/pgx_ulid/archive/refs/tags/v0.1.0.tar.gz -O pgx_ulid.tar.gz && \
echo "908b7358e6f846e87db508ae5349fb56a88ee6305519074b12f3d5b0ff09f791 pgx_ulid.tar.gz" | sha256sum --check && \
mkdir pgx_ulid-src && cd pgx_ulid-src && tar xvzf ../pgx_ulid.tar.gz --strip-components=1 -C . && \
sed -i 's/pgx = "=0.7.3"/pgx = { version = "0.7.3", features = [ "unsafe-postgres" ] }/g' Cargo.toml && \
cargo pgx install --release && \
echo "trusted = true" >> /usr/local/pgsql/share/extension/ulid.control
#########################################################################################
#
# Layer "neon-pg-ext-build"
# compile neon extensions
#
#########################################################################################
FROM build-deps AS neon-pg-ext-build
# Public extensions
COPY --from=postgis-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=postgis-build /sfcgal/* /
COPY --from=plv8-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=h3-pg-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=h3-pg-build /h3/usr /
COPY --from=unit-pg-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=vector-pg-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=pgjwt-pg-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=pg-jsonschema-pg-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=pg-graphql-pg-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=pg-tiktoken-pg-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=hypopg-pg-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=pg-hashids-pg-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=rum-pg-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=pgtap-pg-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=ip4r-pg-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=prefix-pg-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=hll-pg-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=plpgsql-check-pg-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=timescaledb-pg-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=pg-hint-plan-pg-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=kq-imcx-pg-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=pg-cron-pg-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=pg-pgx-ulid-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=rdkit-pg-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=pg-uuidv7-pg-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=pg-roaringbitmap-pg-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=pg-embedding-pg-build /usr/local/pgsql/ /usr/local/pgsql/
COPY pgxn/ pgxn/
RUN make -j $(getconf _NPROCESSORS_ONLN) \
PG_CONFIG=/usr/local/pgsql/bin/pg_config \
-C pgxn/neon \
-s install && \
make -j $(getconf _NPROCESSORS_ONLN) \
PG_CONFIG=/usr/local/pgsql/bin/pg_config \
-C pgxn/neon_utils \
-s install && \
make -j $(getconf _NPROCESSORS_ONLN) \
PG_CONFIG=/usr/local/pgsql/bin/pg_config \
-C pgxn/neon_rmgr \
-s install && \
case "${PG_VERSION}" in \
"v14" | "v15") \
;; \
"v16") \
echo "Skipping HNSW for PostgreSQL 16" && exit 0 \
;; \
*) \
echo "unexpected PostgreSQL version" && exit 1 \
;; \
esac && \
make -j $(getconf _NPROCESSORS_ONLN) \
PG_CONFIG=/usr/local/pgsql/bin/pg_config \
-C pgxn/hnsw \
-s install
#########################################################################################
#
# Compile and run the Neon-specific `compute_ctl` binary
#
#########################################################################################
FROM $REPOSITORY/$IMAGE:$TAG AS compute-tools
ARG BUILD_TAG
ENV BUILD_TAG=$BUILD_TAG
USER nonroot
# Copy entire project to get Cargo.* files with proper dependencies for the whole project
COPY --chown=nonroot . .
RUN cd compute_tools && cargo build --locked --profile release-line-debug-size-lto
#########################################################################################
#
# Clean up postgres folder before inclusion
#
#########################################################################################
FROM neon-pg-ext-build AS postgres-cleanup-layer
COPY --from=neon-pg-ext-build /usr/local/pgsql /usr/local/pgsql
# Remove binaries from /bin/ that we won't use (or would manually copy & install otherwise)
RUN cd /usr/local/pgsql/bin && rm ecpg raster2pgsql shp2pgsql pgtopo_export pgtopo_import pgsql2shp
# Remove headers that we won't need anymore - we've completed installation of all extensions
RUN rm -r /usr/local/pgsql/include
# Remove static postgresql libraries - all compilation is finished, so we
# can now remove these files - they must be included in other binaries by now
# if they were to be used by other libraries.
RUN rm /usr/local/pgsql/lib/lib*.a
#########################################################################################
#
# Final layer
# Put it all together into the final image
#
#########################################################################################
FROM debian:bullseye-slim
# Add user postgres
RUN mkdir /var/db && useradd -m -d /var/db/postgres postgres && \
echo "postgres:test_console_pass" | chpasswd && \
mkdir /var/db/postgres/compute && mkdir /var/db/postgres/specs && \
chown -R postgres:postgres /var/db/postgres && \
chmod 0750 /var/db/postgres/compute && \
echo '/usr/local/lib' >> /etc/ld.so.conf && /sbin/ldconfig && \
# create folder for file cache
mkdir -p -m 777 /neon/cache
COPY --from=postgres-cleanup-layer --chown=postgres /usr/local/pgsql /usr/local
COPY --from=compute-tools --chown=postgres /home/nonroot/target/release-line-debug-size-lto/compute_ctl /usr/local/bin/compute_ctl
# Install:
# libreadline8 for psql
# libicu67, locales for collations (including ICU and plpgsql_check)
# liblz4-1 for lz4
# libossp-uuid16 for extension ossp-uuid
# libgeos, libgdal, libsfcgal1, libproj and libprotobuf-c1 for PostGIS
# libxml2, libxslt1.1 for xml2
# libzstd1 for zstd
# libboost*, libfreetype6, and zlib1g for rdkit
# ca-certificates for communicating with s3 by compute_ctl
RUN apt update && \
apt install --no-install-recommends -y \
gdb \
libicu67 \
liblz4-1 \
libreadline8 \
libboost-iostreams1.74.0 \
libboost-regex1.74.0 \
libboost-serialization1.74.0 \
libboost-system1.74.0 \
libossp-uuid16 \
libfreetype6 \
libgeos-c1v5 \
libgdal28 \
libproj19 \
libprotobuf-c1 \
libsfcgal1 \
libxml2 \
libxslt1.1 \
libzstd1 \
libcurl4-openssl-dev \
locales \
procps \
zlib1g \
ca-certificates && \
rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* && \
localedef -i en_US -c -f UTF-8 -A /usr/share/locale/locale.alias en_US.UTF-8
ENV LANG en_US.utf8
USER postgres
ENTRYPOINT ["/usr/local/bin/compute_ctl"]

220
Dockerfile.compute-node-v14 Normal file
View File

@@ -0,0 +1,220 @@
#
# This file is identical to the Dockerfile.compute-node-v15 file
# except for the version of Postgres that is built.
#
ARG TAG=pinned
#########################################################################################
#
# Layer "build-deps"
#
#########################################################################################
FROM debian:bullseye-slim AS build-deps
RUN apt update && \
apt install -y git autoconf automake libtool build-essential bison flex libreadline-dev \
zlib1g-dev libxml2-dev libcurl4-openssl-dev libossp-uuid-dev wget pkg-config libssl-dev
#########################################################################################
#
# Layer "pg-build"
# Build Postgres from the neon postgres repository.
#
#########################################################################################
FROM build-deps AS pg-build
COPY vendor/postgres-v14 postgres
RUN cd postgres && \
./configure CFLAGS='-O2 -g3' --enable-debug --with-openssl --with-uuid=ossp && \
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 $(getconf _NPROCESSORS_ONLN) -s -C src/interfaces/libpq install && \
# Enable some of contrib extensions
echo 'trusted = true' >> /usr/local/pgsql/share/extension/bloom.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/pgrowlocks.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/intagg.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/pgstattuple.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/earthdistance.control
#########################################################################################
#
# Layer "postgis-build"
# Build PostGIS from the upstream PostGIS mirror.
#
#########################################################################################
FROM build-deps AS postgis-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN apt update && \
apt install -y gdal-bin libgdal-dev libprotobuf-c-dev protobuf-c-compiler xsltproc
RUN wget https://download.osgeo.org/postgis/source/postgis-3.3.1.tar.gz && \
tar xvzf postgis-3.3.1.tar.gz && \
cd postgis-3.3.1 && \
./autogen.sh && \
export PATH="/usr/local/pgsql/bin:$PATH" && \
./configure && \
make -j $(getconf _NPROCESSORS_ONLN) install && \
cd extensions/postgis && \
make clean && \
make -j $(getconf _NPROCESSORS_ONLN) install && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_raster.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_tiger_geocoder.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_topology.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/address_standardizer.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/address_standardizer_data_us.control
#########################################################################################
#
# Layer "plv8-build"
# Build plv8
#
#########################################################################################
FROM build-deps AS plv8-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN apt update && \
apt install -y ninja-build python3-dev libc++-dev libc++abi-dev libncurses5 binutils
# https://github.com/plv8/plv8/issues/475:
# v8 uses gold for linking and sets `--thread-count=4` which breaks
# gold version <= 1.35 (https://sourceware.org/bugzilla/show_bug.cgi?id=23607)
# Install newer gold version manually as debian-testing binutils version updates
# libc version, which in turn breaks other extension built against non-testing libc.
RUN wget https://ftp.gnu.org/gnu/binutils/binutils-2.38.tar.gz && \
tar xvzf binutils-2.38.tar.gz && \
cd binutils-2.38 && \
cd libiberty && ./configure && make -j $(getconf _NPROCESSORS_ONLN) && \
cd ../bfd && ./configure && make bfdver.h && \
cd ../gold && ./configure && make -j $(getconf _NPROCESSORS_ONLN) && make install && \
cp /usr/local/bin/ld.gold /usr/bin/gold
# Sed is used to patch for https://github.com/plv8/plv8/issues/503
RUN wget https://github.com/plv8/plv8/archive/refs/tags/v3.1.4.tar.gz && \
tar xvzf v3.1.4.tar.gz && \
cd plv8-3.1.4 && \
export PATH="/usr/local/pgsql/bin:$PATH" && \
sed -i 's/MemoryContextAlloc(/MemoryContextAllocZero(/' plv8.cc && \
make DOCKER=1 -j $(getconf _NPROCESSORS_ONLN) install && \
rm -rf /plv8-* && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/plv8.control
#########################################################################################
#
# Layer "h3-pg-build"
# Build h3_pg
#
#########################################################################################
FROM build-deps AS h3-pg-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
# packaged cmake is too old
RUN wget https://github.com/Kitware/CMake/releases/download/v3.24.2/cmake-3.24.2-linux-x86_64.sh \
-q -O /tmp/cmake-install.sh \
&& chmod u+x /tmp/cmake-install.sh \
&& /tmp/cmake-install.sh --skip-license --prefix=/usr/local/ \
&& rm /tmp/cmake-install.sh
RUN wget https://github.com/uber/h3/archive/refs/tags/v4.0.1.tar.gz -O h3.tgz && \
tar xvzf h3.tgz && \
cd h3-4.0.1 && \
mkdir build && \
cd build && \
cmake .. -DCMAKE_BUILD_TYPE=Release && \
make -j $(getconf _NPROCESSORS_ONLN) && \
DESTDIR=/h3 make install && \
cp -R /h3/usr / && \
rm -rf build
RUN wget https://github.com/zachasme/h3-pg/archive/refs/tags/v4.0.1.tar.gz -O h3-pg.tgz && \
tar xvzf h3-pg.tgz && \
cd h3-pg-4.0.1 && \
export PATH="/usr/local/pgsql/bin:$PATH" && \
make -j $(getconf _NPROCESSORS_ONLN) && \
make -j $(getconf _NPROCESSORS_ONLN) install && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/h3.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/h3_postgis.control
#########################################################################################
#
# Layer "neon-pg-ext-build"
# compile neon extensions
#
#########################################################################################
FROM build-deps AS neon-pg-ext-build
COPY --from=postgis-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=plv8-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=h3-pg-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=h3-pg-build /h3/usr /
COPY pgxn/ pgxn/
RUN make -j $(getconf _NPROCESSORS_ONLN) \
PG_CONFIG=/usr/local/pgsql/bin/pg_config \
-C pgxn/neon \
-s install
#########################################################################################
#
# Compile and run the Neon-specific `compute_ctl` binary
#
#########################################################################################
FROM 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:$TAG AS compute-tools
USER nonroot
# Copy entire project to get Cargo.* files with proper dependencies for the whole project
COPY --chown=nonroot . .
RUN cd compute_tools && cargo build --locked --profile release-line-debug-size-lto
#########################################################################################
#
# Clean up postgres folder before inclusion
#
#########################################################################################
FROM neon-pg-ext-build AS postgres-cleanup-layer
COPY --from=neon-pg-ext-build /usr/local/pgsql /usr/local/pgsql
# Remove binaries from /bin/ that we won't use (or would manually copy & install otherwise)
RUN cd /usr/local/pgsql/bin && rm ecpg raster2pgsql shp2pgsql pgtopo_export pgtopo_import pgsql2shp
# Remove headers that we won't need anymore - we've completed installation of all extensions
RUN rm -r /usr/local/pgsql/include
# Remove static postgresql libraries - all compilation is finished, so we
# can now remove these files - they must be included in other binaries by now
# if they were to be used by other libraries.
RUN rm /usr/local/pgsql/lib/lib*.a
#########################################################################################
#
# Final layer
# Put it all together into the final image
#
#########################################################################################
FROM debian:bullseye-slim
# Add user postgres
RUN mkdir /var/db && useradd -m -d /var/db/postgres postgres && \
echo "postgres:test_console_pass" | chpasswd && \
mkdir /var/db/postgres/compute && mkdir /var/db/postgres/specs && \
chown -R postgres:postgres /var/db/postgres && \
chmod 0750 /var/db/postgres/compute && \
echo '/usr/local/lib' >> /etc/ld.so.conf && /sbin/ldconfig
COPY --from=postgres-cleanup-layer --chown=postgres /usr/local/pgsql /usr/local
COPY --from=compute-tools --chown=postgres /home/nonroot/target/release-line-debug-size-lto/compute_ctl /usr/local/bin/compute_ctl
# Install:
# libreadline8 for psql
# libossp-uuid16 for extension ossp-uuid
# libgeos, libgdal, libproj and libprotobuf-c1 for PostGIS
RUN apt update && \
apt install --no-install-recommends -y \
libreadline8 \
libossp-uuid16 \
libgeos-c1v5 \
libgdal28 \
libproj19 \
libprotobuf-c1 \
gdb && \
rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
USER postgres
ENTRYPOINT ["/usr/local/bin/compute_ctl"]

220
Dockerfile.compute-node-v15 Normal file
View File

@@ -0,0 +1,220 @@
#
# This file is identical to the Dockerfile.compute-node-v14 file
# except for the version of Postgres that is built.
#
ARG TAG=pinned
#########################################################################################
#
# Layer "build-deps"
#
#########################################################################################
FROM debian:bullseye-slim AS build-deps
RUN apt update && \
apt install -y git autoconf automake libtool build-essential bison flex libreadline-dev \
zlib1g-dev libxml2-dev libcurl4-openssl-dev libossp-uuid-dev wget pkg-config libssl-dev
#########################################################################################
#
# Layer "pg-build"
# Build Postgres from the neon postgres repository.
#
#########################################################################################
FROM build-deps AS pg-build
COPY vendor/postgres-v15 postgres
RUN cd postgres && \
./configure CFLAGS='-O2 -g3' --enable-debug --with-openssl --with-uuid=ossp && \
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 $(getconf _NPROCESSORS_ONLN) -s -C src/interfaces/libpq install && \
# Enable some of contrib extensions
echo 'trusted = true' >> /usr/local/pgsql/share/extension/bloom.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/pgrowlocks.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/intagg.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/pgstattuple.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/earthdistance.control
#########################################################################################
#
# Layer "postgis-build"
# Build PostGIS from the upstream PostGIS mirror.
#
#########################################################################################
FROM build-deps AS postgis-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN apt update && \
apt install -y gdal-bin libgdal-dev libprotobuf-c-dev protobuf-c-compiler xsltproc
RUN wget https://download.osgeo.org/postgis/source/postgis-3.3.1.tar.gz && \
tar xvzf postgis-3.3.1.tar.gz && \
cd postgis-3.3.1 && \
./autogen.sh && \
export PATH="/usr/local/pgsql/bin:$PATH" && \
./configure && \
make -j $(getconf _NPROCESSORS_ONLN) install && \
cd extensions/postgis && \
make clean && \
make -j $(getconf _NPROCESSORS_ONLN) install && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_raster.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_tiger_geocoder.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/postgis_topology.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/address_standardizer.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/address_standardizer_data_us.control
#########################################################################################
#
# Layer "plv8-build"
# Build plv8
#
#########################################################################################
FROM build-deps AS plv8-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN apt update && \
apt install -y ninja-build python3-dev libc++-dev libc++abi-dev libncurses5 binutils
# https://github.com/plv8/plv8/issues/475:
# v8 uses gold for linking and sets `--thread-count=4` which breaks
# gold version <= 1.35 (https://sourceware.org/bugzilla/show_bug.cgi?id=23607)
# Install newer gold version manually as debian-testing binutils version updates
# libc version, which in turn breaks other extension built against non-testing libc.
RUN wget https://ftp.gnu.org/gnu/binutils/binutils-2.38.tar.gz && \
tar xvzf binutils-2.38.tar.gz && \
cd binutils-2.38 && \
cd libiberty && ./configure && make -j $(getconf _NPROCESSORS_ONLN) && \
cd ../bfd && ./configure && make bfdver.h && \
cd ../gold && ./configure && make -j $(getconf _NPROCESSORS_ONLN) && make install && \
cp /usr/local/bin/ld.gold /usr/bin/gold
# Sed is used to patch for https://github.com/plv8/plv8/issues/503
RUN wget https://github.com/plv8/plv8/archive/refs/tags/v3.1.4.tar.gz && \
tar xvzf v3.1.4.tar.gz && \
cd plv8-3.1.4 && \
export PATH="/usr/local/pgsql/bin:$PATH" && \
sed -i 's/MemoryContextAlloc(/MemoryContextAllocZero(/' plv8.cc && \
make DOCKER=1 -j $(getconf _NPROCESSORS_ONLN) install && \
rm -rf /plv8-* && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/plv8.control
#########################################################################################
#
# Layer "h3-pg-build"
# Build h3_pg
#
#########################################################################################
FROM build-deps AS h3-pg-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
# packaged cmake is too old
RUN wget https://github.com/Kitware/CMake/releases/download/v3.24.2/cmake-3.24.2-linux-x86_64.sh \
-q -O /tmp/cmake-install.sh \
&& chmod u+x /tmp/cmake-install.sh \
&& /tmp/cmake-install.sh --skip-license --prefix=/usr/local/ \
&& rm /tmp/cmake-install.sh
RUN wget https://github.com/uber/h3/archive/refs/tags/v4.0.1.tar.gz -O h3.tgz && \
tar xvzf h3.tgz && \
cd h3-4.0.1 && \
mkdir build && \
cd build && \
cmake .. -DCMAKE_BUILD_TYPE=Release && \
make -j $(getconf _NPROCESSORS_ONLN) && \
DESTDIR=/h3 make install && \
cp -R /h3/usr / && \
rm -rf build
RUN wget https://github.com/zachasme/h3-pg/archive/refs/tags/v4.0.1.tar.gz -O h3-pg.tgz && \
tar xvzf h3-pg.tgz && \
cd h3-pg-4.0.1 && \
export PATH="/usr/local/pgsql/bin:$PATH" && \
make -j $(getconf _NPROCESSORS_ONLN) && \
make -j $(getconf _NPROCESSORS_ONLN) install && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/h3.control && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/h3_postgis.control
#########################################################################################
#
# Layer "neon-pg-ext-build"
# compile neon extensions
#
#########################################################################################
FROM build-deps AS neon-pg-ext-build
COPY --from=postgis-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=plv8-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=h3-pg-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=h3-pg-build /h3/usr /
COPY pgxn/ pgxn/
RUN make -j $(getconf _NPROCESSORS_ONLN) \
PG_CONFIG=/usr/local/pgsql/bin/pg_config \
-C pgxn/neon \
-s install
#########################################################################################
#
# Compile and run the Neon-specific `compute_ctl` binary
#
#########################################################################################
FROM 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:$TAG AS compute-tools
USER nonroot
# Copy entire project to get Cargo.* files with proper dependencies for the whole project
COPY --chown=nonroot . .
RUN cd compute_tools && cargo build --locked --profile release-line-debug-size-lto
#########################################################################################
#
# Clean up postgres folder before inclusion
#
#########################################################################################
FROM neon-pg-ext-build AS postgres-cleanup-layer
COPY --from=neon-pg-ext-build /usr/local/pgsql /usr/local/pgsql
# Remove binaries from /bin/ that we won't use (or would manually copy & install otherwise)
RUN cd /usr/local/pgsql/bin && rm ecpg raster2pgsql shp2pgsql pgtopo_export pgtopo_import pgsql2shp
# Remove headers that we won't need anymore - we've completed installation of all extensions
RUN rm -r /usr/local/pgsql/include
# Remove static postgresql libraries - all compilation is finished, so we
# can now remove these files - they must be included in other binaries by now
# if they were to be used by other libraries.
RUN rm /usr/local/pgsql/lib/lib*.a
#########################################################################################
#
# Final layer
# Put it all together into the final image
#
#########################################################################################
FROM debian:bullseye-slim
# Add user postgres
RUN mkdir /var/db && useradd -m -d /var/db/postgres postgres && \
echo "postgres:test_console_pass" | chpasswd && \
mkdir /var/db/postgres/compute && mkdir /var/db/postgres/specs && \
chown -R postgres:postgres /var/db/postgres && \
chmod 0750 /var/db/postgres/compute && \
echo '/usr/local/lib' >> /etc/ld.so.conf && /sbin/ldconfig
COPY --from=postgres-cleanup-layer --chown=postgres /usr/local/pgsql /usr/local
COPY --from=compute-tools --chown=postgres /home/nonroot/target/release-line-debug-size-lto/compute_ctl /usr/local/bin/compute_ctl
# Install:
# libreadline8 for psql
# libossp-uuid16 for extension ossp-uuid
# libgeos, libgdal, libproj and libprotobuf-c1 for PostGIS
RUN apt update && \
apt install --no-install-recommends -y \
libreadline8 \
libossp-uuid16 \
libgeos-c1v5 \
libgdal28 \
libproj19 \
libprotobuf-c1 \
gdb && \
rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
USER postgres
ENTRYPOINT ["/usr/local/bin/compute_ctl"]

View File

@@ -1,9 +1,8 @@
# First transient image to build compute_tools binaries
# NB: keep in sync with rust image version in .github/workflows/build_and_test.yml
ARG REPOSITORY=neondatabase
ARG REPOSITORY=369495373322.dkr.ecr.eu-central-1.amazonaws.com
ARG IMAGE=rust
ARG TAG=pinned
ARG BUILD_TAG
FROM $REPOSITORY/$IMAGE:$TAG AS rust-build
WORKDIR /home/nonroot
@@ -17,8 +16,6 @@ ENV CACHEPOT_S3_KEY_PREFIX=cachepot
ARG CACHEPOT_BUCKET=neon-github-dev
#ARG AWS_ACCESS_KEY_ID
#ARG AWS_SECRET_ACCESS_KEY
ARG BUILD_TAG
ENV BUILD_TAG=$BUILD_TAG
COPY . .

View File

@@ -29,7 +29,6 @@ else ifeq ($(UNAME_S),Darwin)
# It can be configured with OPENSSL_PREFIX variable
OPENSSL_PREFIX ?= $(shell brew --prefix openssl@3)
PG_CONFIGURE_OPTS += --with-includes=$(OPENSSL_PREFIX)/include --with-libraries=$(OPENSSL_PREFIX)/lib
PG_CONFIGURE_OPTS += PKG_CONFIG_PATH=$(shell brew --prefix icu4c)/lib/pkgconfig
# macOS already has bison and flex in the system, but they are old and result in postgres-v14 target failure
# brew formulae are keg-only and not symlinked into HOMEBREW_PREFIX, force their usage
EXTRA_PATH_OVERRIDES += $(shell brew --prefix bison)/bin/:$(shell brew --prefix flex)/bin/:
@@ -84,8 +83,6 @@ $(POSTGRES_INSTALL_DIR)/build/%/config.status:
# I'm not sure why it wouldn't work, but this is the only place (apart from
# the "build-all-versions" entry points) where direct mention of PostgreSQL
# versions is used.
.PHONY: postgres-configure-v16
postgres-configure-v16: $(POSTGRES_INSTALL_DIR)/build/v16/config.status
.PHONY: postgres-configure-v15
postgres-configure-v15: $(POSTGRES_INSTALL_DIR)/build/v15/config.status
.PHONY: postgres-configure-v14
@@ -111,8 +108,6 @@ postgres-%: postgres-configure-% \
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pg_buffercache install
+@echo "Compiling pageinspect $*"
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pageinspect install
+@echo "Compiling amcheck $*"
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/amcheck install
.PHONY: postgres-clean-%
postgres-clean-%:
@@ -121,10 +116,6 @@ postgres-clean-%:
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pageinspect clean
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/src/interfaces/libpq clean
.PHONY: postgres-check-%
postgres-check-%: postgres-%
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$* MAKELEVEL=0 check
.PHONY: neon-pg-ext-%
neon-pg-ext-%: postgres-%
+@echo "Compiling neon $*"
@@ -137,73 +128,43 @@ neon-pg-ext-%: postgres-%
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-walredo-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_walredo/Makefile install
+@echo "Compiling neon_rmgr $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-rmgr-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-rmgr-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_rmgr/Makefile install
+@echo "Compiling neon_test_utils $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_test_utils/Makefile install
+@echo "Compiling neon_utils $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-utils-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-utils-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_utils/Makefile install
.PHONY: neon-pg-ext-clean-%
neon-pg-ext-clean-%:
$(MAKE) PG_CONFIG=$(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
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/pgxn/neon-$* -f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile clean
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/pgxn/neon_walredo-$* -f $(ROOT_PROJECT_DIR)/pgxn/neon_walredo/Makefile clean
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/pgxn/neon_test_utils-$* -f $(ROOT_PROJECT_DIR)/pgxn/neon_test_utils/Makefile clean
.PHONY: neon-pg-ext
neon-pg-ext: \
neon-pg-ext-v14 \
neon-pg-ext-v15 \
neon-pg-ext-v16
neon-pg-ext-v15
.PHONY: neon-pg-ext-clean
neon-pg-ext-clean: \
neon-pg-ext-clean-v14 \
neon-pg-ext-clean-v15 \
neon-pg-ext-clean-v16
neon-pg-ext-clean-v15
# shorthand to build all Postgres versions
.PHONY: postgres
postgres: \
postgres-v14 \
postgres-v15 \
postgres-v16
postgres-v15
.PHONY: postgres-headers
postgres-headers: \
postgres-headers-v14 \
postgres-headers-v15 \
postgres-headers-v16
postgres-headers-v15
.PHONY: postgres-clean
postgres-clean: \
postgres-clean-v14 \
postgres-clean-v15 \
postgres-clean-v16
.PHONY: postgres-check
postgres-check: \
postgres-check-v14 \
postgres-check-v15 \
postgres-check-v16
postgres-clean-v15
# This doesn't remove the effects of 'configure'.
.PHONY: clean

View File

@@ -1,5 +1,3 @@
[![Neon](https://user-images.githubusercontent.com/13738772/236813940-dcfdcb5b-69d3-449b-a686-013febe834d4.png)](https://neon.tech)
# Neon
Neon is a serverless open-source alternative to AWS Aurora Postgres. It separates storage and compute and substitutes the PostgreSQL storage layer by redistributing data across a cluster of nodes.
@@ -17,7 +15,7 @@ The Neon storage engine consists of two major components:
- Pageserver. Scalable storage backend for the compute nodes.
- Safekeepers. The safekeepers form a redundant WAL service that received WAL from the compute node, and stores it durably until it has been processed by the pageserver and uploaded to cloud storage.
See developer documentation in [SUMMARY.md](/docs/SUMMARY.md) for more information.
See developer documentation in [/docs/SUMMARY.md](/docs/SUMMARY.md) for more information.
## Running local installation
@@ -28,22 +26,14 @@ See developer documentation in [SUMMARY.md](/docs/SUMMARY.md) for more informati
* On Ubuntu or Debian, this set of packages should be sufficient to build the code:
```bash
apt install build-essential libtool libreadline-dev zlib1g-dev flex bison libseccomp-dev \
libssl-dev clang pkg-config libpq-dev cmake postgresql-client protobuf-compiler \
libcurl4-openssl-dev openssl python-poetry lsof libicu-dev
libssl-dev clang pkg-config libpq-dev cmake postgresql-client protobuf-compiler
```
* On Fedora, these packages are needed:
```bash
dnf install flex bison readline-devel zlib-devel openssl-devel \
libseccomp-devel perl clang cmake postgresql postgresql-contrib protobuf-compiler \
protobuf-devel libcurl-devel openssl poetry lsof libicu-devel
protobuf-devel
```
* On Arch based systems, these packages are needed:
```bash
pacman -S base-devel readline zlib libseccomp openssl clang \
postgresql-libs cmake postgresql protobuf curl lsof
```
Building Neon requires 3.15+ version of `protoc` (protobuf-compiler). If your distribution provides an older version, you can install a newer version from [here](https://github.com/protocolbuffers/protobuf/releases).
2. [Install Rust](https://www.rust-lang.org/tools/install)
```
@@ -51,14 +41,11 @@ Building Neon requires 3.15+ version of `protoc` (protobuf-compiler). If your di
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
```
#### Installing dependencies on macOS (12.3.1)
#### Installing dependencies on OSX (12.3.1)
1. Install XCode and dependencies
```
xcode-select --install
brew install protobuf openssl flex bison icu4c pkg-config
# add openssl to PATH, required for ed25519 keys generation in neon_local
echo 'export PATH="$(brew --prefix openssl)/bin:$PATH"' >> ~/.zshrc
brew install protobuf openssl flex bison
```
2. [Install Rust](https://www.rust-lang.org/tools/install)
@@ -96,10 +83,9 @@ cd neon
# The preferred and default is to make a debug build. This will create a
# demonstrably slower build than a release build. For a release build,
# use "BUILD_TYPE=release make -j`nproc` -s"
# Remove -s for the verbose build log
# use "BUILD_TYPE=release make -j`nproc`"
make -j`nproc` -s
make -j`nproc`
```
#### Building on OSX
@@ -113,17 +99,16 @@ cd neon
# The preferred and default is to make a debug build. This will create a
# demonstrably slower build than a release build. For a release build,
# use "BUILD_TYPE=release make -j`sysctl -n hw.logicalcpu` -s"
# Remove -s for the verbose build log
# use "BUILD_TYPE=release make -j`sysctl -n hw.logicalcpu`"
make -j`sysctl -n hw.logicalcpu` -s
make -j`sysctl -n hw.logicalcpu`
```
#### Dependency installation notes
To run the `psql` client, install the `postgresql-client` package or modify `PATH` and `LD_LIBRARY_PATH` to include `pg_install/bin` and `pg_install/lib`, respectively.
To run the integration tests or Python scripts (not required to use the code), install
Python (3.9 or higher), and install python3 packages using `./scripts/pysync` (requires [poetry>=1.3](https://python-poetry.org/)) in the project directory.
Python (3.9 or higher), and install python3 packages using `./scripts/pysync` (requires [poetry](https://python-poetry.org/)) in the project directory.
#### Running neon database
@@ -131,33 +116,34 @@ Python (3.9 or higher), and install python3 packages using `./scripts/pysync` (r
```sh
# Create repository in .neon with proper paths to binaries and data
# Later that would be responsibility of a package install script
> cargo neon init
Initializing pageserver node 1 at '127.0.0.1:64000' in ".neon"
> ./target/debug/neon_local init
Starting pageserver at '127.0.0.1:64000' in '.neon'.
# start pageserver, safekeeper, and broker for their intercommunication
> cargo neon start
Starting neon broker at 127.0.0.1:50051.
> ./target/debug/neon_local start
Starting neon broker at 127.0.0.1:50051
storage_broker started, pid: 2918372
Starting pageserver node 1 at '127.0.0.1:64000' in ".neon".
Starting pageserver at '127.0.0.1:64000' in '.neon'.
pageserver started, pid: 2918386
Starting safekeeper at '127.0.0.1:5454' in '.neon/safekeepers/sk1'.
safekeeper 1 started, pid: 2918437
# create initial tenant and use it as a default for every future neon_local invocation
> cargo neon tenant create --set-default
> ./target/debug/neon_local tenant create --set-default
tenant 9ef87a5bf0d92544f6fafeeb3239695c successfully created on the pageserver
Created an initial timeline 'de200bd42b49cc1814412c7e592dd6e9' at Lsn 0/16B5A50 for tenant: 9ef87a5bf0d92544f6fafeeb3239695c
Setting tenant 9ef87a5bf0d92544f6fafeeb3239695c as a default one
# start postgres compute node
> cargo neon endpoint start main
Starting new endpoint main (PostgreSQL v14) on timeline de200bd42b49cc1814412c7e592dd6e9 ...
Starting postgres at 'postgresql://cloud_admin@127.0.0.1:55432/postgres'
> ./target/debug/neon_local pg start main
Starting new postgres (v14) main on timeline de200bd42b49cc1814412c7e592dd6e9 ...
Extracting base backup to create postgres instance: path=.neon/pgdatadirs/tenants/9ef87a5bf0d92544f6fafeeb3239695c/main port=55432
Starting postgres node at 'host=127.0.0.1 port=55432 user=cloud_admin dbname=postgres'
# check list of running postgres instances
> cargo neon endpoint list
ENDPOINT ADDRESS TIMELINE BRANCH NAME LSN STATUS
main 127.0.0.1:55432 de200bd42b49cc1814412c7e592dd6e9 main 0/16B5BA8 running
> ./target/debug/neon_local pg list
NODE ADDRESS TIMELINE BRANCH NAME LSN STATUS
main 127.0.0.1:55432 de200bd42b49cc1814412c7e592dd6e9 main 0/16B5BA8 running
```
2. Now, it is possible to connect to postgres and run some queries:
@@ -177,28 +163,29 @@ postgres=# select * from t;
3. And create branches and run postgres on them:
```sh
# create branch named migration_check
> cargo neon timeline branch --branch-name migration_check
> ./target/debug/neon_local timeline branch --branch-name migration_check
Created timeline 'b3b863fa45fa9e57e615f9f2d944e601' at Lsn 0/16F9A00 for tenant: 9ef87a5bf0d92544f6fafeeb3239695c. Ancestor timeline: 'main'
# check branches tree
> cargo neon timeline list
> ./target/debug/neon_local timeline list
(L) main [de200bd42b49cc1814412c7e592dd6e9]
(L) ┗━ @0/16F9A00: migration_check [b3b863fa45fa9e57e615f9f2d944e601]
# start postgres on that branch
> cargo neon endpoint start migration_check --branch-name migration_check
Starting new endpoint migration_check (PostgreSQL v14) on timeline b3b863fa45fa9e57e615f9f2d944e601 ...
Starting postgres at 'postgresql://cloud_admin@127.0.0.1:55434/postgres'
> ./target/debug/neon_local pg start migration_check --branch-name migration_check
Starting new postgres migration_check on timeline b3b863fa45fa9e57e615f9f2d944e601 ...
Extracting base backup to create postgres instance: path=.neon/pgdatadirs/tenants/9ef87a5bf0d92544f6fafeeb3239695c/migration_check port=55433
Starting postgres node at 'host=127.0.0.1 port=55433 user=cloud_admin dbname=postgres'
# check the new list of running postgres instances
> cargo neon endpoint list
ENDPOINT ADDRESS TIMELINE BRANCH NAME LSN STATUS
> ./target/debug/neon_local pg list
NODE ADDRESS TIMELINE BRANCH NAME LSN STATUS
main 127.0.0.1:55432 de200bd42b49cc1814412c7e592dd6e9 main 0/16F9A38 running
migration_check 127.0.0.1:55434 b3b863fa45fa9e57e615f9f2d944e601 migration_check 0/16F9A70 running
migration_check 127.0.0.1:55433 b3b863fa45fa9e57e615f9f2d944e601 migration_check 0/16F9A70 running
# this new postgres instance will have all the data from 'main' postgres,
# but all modifications would not affect data in original postgres
> psql -p55434 -h 127.0.0.1 -U cloud_admin postgres
> psql -p55433 -h 127.0.0.1 -U cloud_admin postgres
postgres=# select * from t;
key | value
-----+-------
@@ -220,7 +207,7 @@ postgres=# select * from t;
4. If you want to run tests afterward (see below), you must stop all the running of the pageserver, safekeeper, and postgres instances
you have just started. You can terminate them all with one command:
```sh
> cargo neon stop
> ./target/debug/neon_local stop
```
## Running tests
@@ -235,18 +222,11 @@ CARGO_BUILD_FLAGS="--features=testing" make
./scripts/pytest
```
By default, this runs both debug and release modes, and all supported postgres versions. When
testing locally, it is convenient to run just run one set of permutations, like this:
```sh
DEFAULT_PG_VERSION=15 BUILD_TYPE=release ./scripts/pytest
```
## Documentation
[docs](/docs) Contains a top-level overview of all available markdown documentation.
[/docs/](/docs/) Contains a top-level overview of all available markdown documentation.
- [sourcetree.md](/docs/sourcetree.md) contains overview of source tree layout.
- [/docs/sourcetree.md](/docs/sourcetree.md) contains overview of source tree layout.
To view your `rustdoc` documentation in a browser, try running `cargo doc --no-deps --open`
@@ -271,6 +251,6 @@ To get more familiar with this aspect, refer to:
## Join the development
- Read [CONTRIBUTING.md](/CONTRIBUTING.md) to learn about project code style and practices.
- To get familiar with a source tree layout, use [sourcetree.md](/docs/sourcetree.md).
- Read `CONTRIBUTING.md` to learn about project code style and practices.
- To get familiar with a source tree layout, use [/docs/sourcetree.md](/docs/sourcetree.md).
- To learn more about PostgreSQL internals, check http://www.interdb.jp/pg/index.html

View File

@@ -1,5 +0,0 @@
disallowed-methods = [
"tokio::task::block_in_place",
# Allow this for now, to deny it later once we stop using Handle::block_on completely
# "tokio::runtime::Handle::block_on",
]

View File

@@ -6,35 +6,20 @@ license.workspace = true
[dependencies]
anyhow.workspace = true
async-compression.workspace = true
chrono.workspace = true
cfg-if.workspace = true
clap.workspace = true
flate2.workspace = true
futures.workspace = true
hyper = { workspace = true, features = ["full"] }
notify.workspace = true
num_cpus.workspace = true
opentelemetry.workspace = true
postgres.workspace = true
regex.workspace = true
serde.workspace = true
serde_json.workspace = true
tar.workspace = true
reqwest = { workspace = true, features = ["json"] }
tokio = { workspace = true, features = ["rt", "rt-multi-thread"] }
tokio-postgres.workspace = true
tokio-util.workspace = true
tracing.workspace = true
tracing-opentelemetry.workspace = true
tracing-subscriber.workspace = true
tracing-utils.workspace = true
url.workspace = true
compute_api.workspace = true
utils.workspace = true
workspace_hack.workspace = true
toml_edit.workspace = true
remote_storage = { version = "0.1", path = "../libs/remote_storage/" }
vm_monitor = { version = "0.1", path = "../libs/vm_monitor/" }
zstd = "0.12.4"

View File

@@ -19,10 +19,9 @@ Also `compute_ctl` spawns two separate service threads:
- `http-endpoint` runs a Hyper HTTP API server, which serves readiness and the
last activity requests.
If `AUTOSCALING` environment variable is set, `compute_ctl` will start the
`vm-monitor` located in [`neon/libs/vm_monitor`]. For VM compute nodes,
`vm-monitor` communicates with the VM autoscaling system. It coordinates
downscaling and requests immediate upscaling under resource pressure.
If the `vm-informant` binary is present at `/bin/vm-informant`, it will also be started. For VM
compute nodes, `vm-informant` communicates with the VM autoscaling system. It coordinates
downscaling and (eventually) will request immediate upscaling under resource pressure.
Usage example:
```sh

View File

@@ -5,8 +5,6 @@
//! - `compute_ctl` accepts cluster (compute node) specification as a JSON file.
//! - Every start is a fresh start, so the data directory is removed and
//! initialized again on each run.
//! - If remote_extension_config is provided, it will be used to fetch extensions list
//! and download `shared_preload_libraries` from the remote storage.
//! - Next it will put configuration files into the `PGDATA` directory.
//! - Sync safekeepers and get commit LSN.
//! - Get `basebackup` from pageserver using the returned on the previous step LSN.
@@ -20,249 +18,117 @@
//! - `http-endpoint` runs a Hyper HTTP API server, which serves readiness and the
//! last activity requests.
//!
//! If `AUTOSCALING` environment variable is set, `compute_ctl` will start the
//! `vm-monitor` located in [`neon/libs/vm_monitor`]. For VM compute nodes,
//! `vm-monitor` communicates with the VM autoscaling system. It coordinates
//! downscaling and requests immediate upscaling under resource pressure.
//! If the `vm-informant` binary is present at `/bin/vm-informant`, it will also be started. For VM
//! compute nodes, `vm-informant` communicates with the VM autoscaling system. It coordinates
//! downscaling and (eventually) will request immediate upscaling under resource pressure.
//!
//! Usage example:
//! ```sh
//! compute_ctl -D /var/db/postgres/compute \
//! -C 'postgresql://cloud_admin@localhost/postgres' \
//! -S /var/db/postgres/specs/current.json \
//! -b /usr/local/bin/postgres \
//! -r {"bucket": "neon-dev-extensions-eu-central-1", "region": "eu-central-1"}
//! -b /usr/local/bin/postgres
//! ```
//!
use std::collections::HashMap;
use std::fs::File;
use std::panic;
use std::path::Path;
use std::process::exit;
use std::sync::{mpsc, Arc, Condvar, Mutex, RwLock};
use std::sync::{Arc, RwLock};
use std::{thread, time::Duration};
use anyhow::{Context, Result};
use chrono::Utc;
use clap::Arg;
use tracing::{error, info};
use url::Url;
use compute_api::responses::ComputeStatus;
use compute_tools::compute::{ComputeNode, ComputeState, ParsedSpec};
use compute_tools::configurator::launch_configurator;
use compute_tools::extension_server::{get_pg_version, init_remote_storage};
use compute_tools::compute::{ComputeMetrics, ComputeNode, ComputeState, ComputeStatus};
use compute_tools::http::api::launch_http_server;
use compute_tools::informant::spawn_vm_informant_if_present;
use compute_tools::logger::*;
use compute_tools::monitor::launch_monitor;
use compute_tools::params::*;
use compute_tools::pg_helpers::*;
use compute_tools::spec::*;
// this is an arbitrary build tag. Fine as a default / for testing purposes
// in-case of not-set environment var
const BUILD_TAG_DEFAULT: &str = "5670669815";
use url::Url;
fn main() -> Result<()> {
init_tracing_and_logging(DEFAULT_LOG_LEVEL)?;
let build_tag = option_env!("BUILD_TAG")
.unwrap_or(BUILD_TAG_DEFAULT)
.to_string();
info!("build_tag: {build_tag}");
init_logger(DEFAULT_LOG_LEVEL)?;
let matches = cli().get_matches();
let pgbin_default = String::from("postgres");
let pgbin = matches.get_one::<String>("pgbin").unwrap_or(&pgbin_default);
let remote_ext_config = matches.get_one::<String>("remote-ext-config");
let ext_remote_storage = remote_ext_config.map(|x| {
init_remote_storage(x).expect("cannot initialize remote extension storage from config")
});
let http_port = *matches
.get_one::<u16>("http-port")
.expect("http-port is required");
let pgdata = matches
.get_one::<String>("pgdata")
.expect("PGDATA path is required");
let connstr = matches
.get_one::<String>("connstr")
.expect("Postgres connection string is required");
let spec_json = matches.get_one::<String>("spec");
let spec = matches.get_one::<String>("spec");
let spec_path = matches.get_one::<String>("spec-path");
// Extract OpenTelemetry context for the startup actions from the
// TRACEPARENT and TRACESTATE env variables, and attach it to the current
// tracing context.
//
// This is used to propagate the context for the 'start_compute' operation
// from the neon control plane. This allows linking together the wider
// 'start_compute' operation that creates the compute container, with the
// startup actions here within the container.
//
// There is no standard for passing context in env variables, but a lot of
// tools use TRACEPARENT/TRACESTATE, so we use that convention too. See
// https://github.com/open-telemetry/opentelemetry-specification/issues/740
//
// Switch to the startup context here, and exit it once the startup has
// completed and Postgres is up and running.
//
// If this pod is pre-created without binding it to any particular endpoint
// yet, this isn't the right place to enter the startup context. In that
// case, the control plane should pass the tracing context as part of the
// /configure API call.
//
// NOTE: This is supposed to only cover the *startup* actions. Once
// postgres is configured and up-and-running, we exit this span. Any other
// actions that are performed on incoming HTTP requests, for example, are
// performed in separate spans.
//
// XXX: If the pod is restarted, we perform the startup actions in the same
// context as the original startup actions, which probably doesn't make
// sense.
let mut startup_tracing_carrier: HashMap<String, String> = HashMap::new();
if let Ok(val) = std::env::var("TRACEPARENT") {
startup_tracing_carrier.insert("traceparent".to_string(), val);
}
if let Ok(val) = std::env::var("TRACESTATE") {
startup_tracing_carrier.insert("tracestate".to_string(), val);
}
let startup_context_guard = if !startup_tracing_carrier.is_empty() {
use opentelemetry::propagation::TextMapPropagator;
use opentelemetry::sdk::propagation::TraceContextPropagator;
let guard = TraceContextPropagator::new()
.extract(&startup_tracing_carrier)
.attach();
info!("startup tracing context attached");
Some(guard)
} else {
None
};
// Try to use just 'postgres' if no path is provided
let pgbin = matches.get_one::<String>("pgbin").unwrap();
let compute_id = matches.get_one::<String>("compute-id");
let control_plane_uri = matches.get_one::<String>("control-plane-uri");
let spec;
let mut live_config_allowed = false;
match spec_json {
let spec: ComputeSpec = match spec {
// First, try to get cluster spec from the cli argument
Some(json) => {
info!("got spec from cli argument {}", json);
spec = Some(serde_json::from_str(json)?);
}
Some(json) => serde_json::from_str(json)?,
None => {
// Second, try to read it from the file if path is provided
if let Some(sp) = spec_path {
let path = Path::new(sp);
let file = File::open(path)?;
spec = Some(serde_json::from_reader(file)?);
} else if let Some(id) = compute_id {
if let Some(cp_base) = control_plane_uri {
live_config_allowed = true;
spec = match get_spec_from_control_plane(cp_base, id) {
Ok(s) => s,
Err(e) => {
error!("cannot get response from control plane: {}", e);
panic!("neither spec nor confirmation that compute is in the Empty state was received");
}
};
} else {
panic!("must specify both --control-plane-uri and --compute-id or none");
}
serde_json::from_reader(file)?
} else {
panic!(
"compute spec should be provided by one of the following ways: \
--spec OR --spec-path OR --control-plane-uri and --compute-id"
);
panic!("cluster spec should be provided via --spec or --spec-path argument");
}
}
};
let mut new_state = ComputeState::new();
let spec_set;
let pageserver_connstr = spec
.cluster
.settings
.find("neon.pageserver_connstring")
.expect("pageserver connstr should be provided");
let tenant = spec
.cluster
.settings
.find("neon.tenant_id")
.expect("tenant id should be provided");
let timeline = spec
.cluster
.settings
.find("neon.timeline_id")
.expect("tenant id should be provided");
if let Some(spec) = spec {
let pspec = ParsedSpec::try_from(spec).map_err(|msg| anyhow::anyhow!(msg))?;
info!("new pspec.spec: {:?}", pspec.spec);
new_state.pspec = Some(pspec);
spec_set = true;
} else {
spec_set = false;
}
let compute_node = ComputeNode {
let compute_state = ComputeNode {
start_time: Utc::now(),
connstr: Url::parse(connstr).context("cannot parse connstr as a URL")?,
pgdata: pgdata.to_string(),
pgbin: pgbin.to_string(),
pgversion: get_pg_version(pgbin),
live_config_allowed,
state: Mutex::new(new_state),
state_changed: Condvar::new(),
ext_remote_storage,
ext_download_progress: RwLock::new(HashMap::new()),
build_tag,
spec,
tenant,
timeline,
pageserver_connstr,
metrics: ComputeMetrics::default(),
state: RwLock::new(ComputeState::new()),
};
let compute = Arc::new(compute_node);
let compute = Arc::new(compute_state);
// If this is a pooled VM, prewarm before starting HTTP server and becoming
// available for binding. Prewarming helps postgres start quicker later,
// because QEMU will already have it's memory allocated from the host, and
// the necessary binaries will alreaady be cached.
if !spec_set {
compute.prewarm_postgres()?;
}
// Launch http service first, so we were able to serve control-plane
// Launch service threads first, so we were able to serve availability
// requests, while configuration is still in progress.
let _http_handle =
launch_http_server(http_port, &compute).expect("cannot launch http endpoint thread");
let extension_server_port: u16 = http_port;
if !spec_set {
// No spec provided, hang waiting for it.
info!("no compute spec provided, waiting");
let mut state = compute.state.lock().unwrap();
while state.status != ComputeStatus::ConfigurationPending {
state = compute.state_changed.wait(state).unwrap();
if state.status == ComputeStatus::ConfigurationPending {
info!("got spec, continue configuration");
// Spec is already set by the http server handler.
break;
}
}
}
// We got all we need, update the state.
let mut state = compute.state.lock().unwrap();
// Record for how long we slept waiting for the spec.
state.metrics.wait_for_spec_ms = Utc::now()
.signed_duration_since(state.start_time)
.to_std()
.unwrap()
.as_millis() as u64;
// Reset start time to the actual start of the configuration, so that
// total startup time was properly measured at the end.
state.start_time = Utc::now();
state.status = ComputeStatus::Init;
compute.state_changed.notify_all();
drop(state);
// Launch remaining service threads
let _monitor_handle = launch_monitor(&compute);
let _configurator_handle = launch_configurator(&compute);
let _http_handle = launch_http_server(&compute).expect("cannot launch http endpoint thread");
let _monitor_handle = launch_monitor(&compute).expect("cannot launch compute monitor thread");
// Also spawn the thread responsible for handling the VM informant -- if it's present
let _vm_informant_handle = spawn_vm_informant_if_present().expect("cannot launch VM informant");
// Start Postgres
let mut delay_exit = false;
let mut exit_code = None;
let pg = match compute.start_compute(extension_server_port) {
let pg = match compute.start_compute() {
Ok(pg) => Some(pg),
Err(err) => {
error!("could not start the compute node: {:?}", err);
let mut state = compute.state.lock().unwrap();
let mut state = compute.state.write().unwrap();
state.error = Some(format!("{:?}", err));
state.status = ComputeStatus::Failed;
drop(state);
@@ -271,63 +137,9 @@ fn main() -> Result<()> {
}
};
// Start the vm-monitor if directed to. The vm-monitor only runs on linux
// because it requires cgroups.
cfg_if::cfg_if! {
if #[cfg(target_os = "linux")] {
use std::env;
use tokio_util::sync::CancellationToken;
use tracing::warn;
let vm_monitor_addr = matches.get_one::<String>("vm-monitor-addr");
let file_cache_connstr = matches.get_one::<String>("filecache-connstr");
let cgroup = matches.get_one::<String>("cgroup");
let file_cache_on_disk = matches.get_flag("file-cache-on-disk");
// Only make a runtime if we need to.
// Note: it seems like you can make a runtime in an inner scope and
// if you start a task in it it won't be dropped. However, make it
// in the outermost scope just to be safe.
let rt = match (env::var_os("AUTOSCALING"), vm_monitor_addr) {
(None, None) => None,
(None, Some(_)) => {
warn!("--vm-monitor-addr option set but AUTOSCALING env var not present");
None
}
(Some(_), None) => {
panic!("AUTOSCALING env var present but --vm-monitor-addr option not set")
}
(Some(_), Some(_)) => Some(
tokio::runtime::Builder::new_multi_thread()
.worker_threads(4)
.enable_all()
.build()
.expect("failed to create tokio runtime for monitor"),
),
};
// This token is used internally by the monitor to clean up all threads
let token = CancellationToken::new();
let vm_monitor = &rt.as_ref().map(|rt| {
rt.spawn(vm_monitor::start(
Box::leak(Box::new(vm_monitor::Args {
cgroup: cgroup.cloned(),
pgconnstr: file_cache_connstr.cloned(),
addr: vm_monitor_addr.cloned().unwrap(),
file_cache_on_disk,
})),
token.clone(),
))
});
}
}
// Wait for the child Postgres process forever. In this state Ctrl+C will
// propagate to Postgres and it will be shut down as well.
if let Some(mut pg) = pg {
// Startup is finished, exit the startup tracing span
drop(startup_context_guard);
let ecode = pg
.wait()
.expect("failed to start waiting on Postgres process");
@@ -335,34 +147,6 @@ fn main() -> Result<()> {
exit_code = ecode.code()
}
// Terminate the vm_monitor so it releases the file watcher on
// /sys/fs/cgroup/neon-postgres.
// Note: the vm-monitor only runs on linux because it requires cgroups.
cfg_if::cfg_if! {
if #[cfg(target_os = "linux")] {
if let Some(handle) = vm_monitor {
// Kills all threads spawned by the monitor
token.cancel();
// Kills the actual task running the monitor
handle.abort();
// If handle is some, rt must have been used to produce it, and
// hence is also some
rt.unwrap().shutdown_timeout(Duration::from_secs(2));
}
}
}
// Maybe sync safekeepers again, to speed up next startup
let compute_state = compute.state.lock().unwrap().clone();
let pspec = compute_state.pspec.as_ref().expect("spec must be set");
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 = compute.sync_safekeepers(storage_auth_token)?;
info!("synced safekeepers at lsn {lsn}");
}
if let Err(err) = compute.check_for_core_dumps() {
error!("error while checking for core dumps: {err:?}");
}
@@ -372,29 +156,9 @@ fn main() -> Result<()> {
if delay_exit {
info!("giving control plane 30s to collect the error before shutdown");
thread::sleep(Duration::from_secs(30));
info!("shutting down");
}
// Shutdown trace pipeline gracefully, so that it has a chance to send any
// pending traces before we exit. Shutting down OTEL tracing provider may
// hang for quite some time, see, for example:
// - https://github.com/open-telemetry/opentelemetry-rust/issues/868
// - and our problems with staging https://github.com/neondatabase/cloud/issues/3707#issuecomment-1493983636
//
// Yet, we want computes to shut down fast enough, as we may need a new one
// for the same timeline ASAP. So wait no longer than 2s for the shutdown to
// complete, then just error out and exit the main thread.
info!("shutting down tracing");
let (sender, receiver) = mpsc::channel();
let _ = thread::spawn(move || {
tracing_utils::shutdown_tracing();
sender.send(()).ok()
});
let shutdown_res = receiver.recv_timeout(Duration::from_millis(2000));
if shutdown_res.is_err() {
error!("timed out while shutting down tracing, exiting anyway");
}
info!("shutting down");
exit(exit_code.unwrap_or(1))
}
@@ -403,14 +167,6 @@ fn cli() -> clap::Command {
let version = option_env!("CARGO_PKG_VERSION").unwrap_or("unknown");
clap::Command::new("compute_ctl")
.version(version)
.arg(
Arg::new("http-port")
.long("http-port")
.value_name("HTTP_PORT")
.default_value("3080")
.value_parser(clap::value_parser!(u16))
.required(false),
)
.arg(
Arg::new("connstr")
.short('C')
@@ -444,52 +200,6 @@ fn cli() -> clap::Command {
.long("spec-path")
.value_name("SPEC_PATH"),
)
.arg(
Arg::new("compute-id")
.short('i')
.long("compute-id")
.value_name("COMPUTE_ID"),
)
.arg(
Arg::new("control-plane-uri")
.short('p')
.long("control-plane-uri")
.value_name("CONTROL_PLANE_API_BASE_URI"),
)
.arg(
Arg::new("remote-ext-config")
.short('r')
.long("remote-ext-config")
.value_name("REMOTE_EXT_CONFIG"),
)
// TODO(fprasx): we currently have default arguments because the cloud PR
// to pass them in hasn't been merged yet. We should get rid of them once
// the PR is merged.
.arg(
Arg::new("vm-monitor-addr")
.long("vm-monitor-addr")
.default_value("0.0.0.0:10301")
.value_name("VM_MONITOR_ADDR"),
)
.arg(
Arg::new("cgroup")
.long("cgroup")
.default_value("neon-postgres")
.value_name("CGROUP"),
)
.arg(
Arg::new("filecache-connstr")
.long("filecache-connstr")
.default_value(
"host=localhost port=5432 dbname=postgres user=cloud_admin sslmode=disable",
)
.value_name("FILECACHE_CONNSTR"),
)
.arg(
Arg::new("file-cache-on-disk")
.long("file-cache-on-disk")
.action(clap::ArgAction::SetTrue),
)
}
#[test]

View File

@@ -1,79 +1,45 @@
use anyhow::{anyhow, Ok, Result};
use anyhow::{anyhow, Result};
use postgres::Client;
use tokio_postgres::NoTls;
use tracing::{error, instrument, warn};
use tracing::{error, instrument};
use crate::compute::ComputeNode;
/// Create a special service table for availability checks
/// only if it does not exist already.
pub fn create_availability_check_data(client: &mut Client) -> Result<()> {
#[instrument(skip_all)]
pub fn create_writability_check_data(client: &mut Client) -> Result<()> {
let query = "
DO $$
BEGIN
IF NOT EXISTS(
SELECT 1
FROM pg_catalog.pg_tables
WHERE tablename = 'health_check'
)
THEN
CREATE TABLE health_check (
id serial primary key,
updated_at timestamptz default now()
);
INSERT INTO health_check VALUES (1, now())
ON CONFLICT (id) DO UPDATE
SET updated_at = now();
END IF;
END
$$;";
client.execute(query, &[])?;
CREATE TABLE IF NOT EXISTS health_check (
id serial primary key,
updated_at timestamptz default now()
);
INSERT INTO health_check VALUES (1, now())
ON CONFLICT (id) DO UPDATE
SET updated_at = now();";
let result = client.simple_query(query)?;
if result.len() < 2 {
return Err(anyhow::format_err!("executed {} queries", result.len()));
}
Ok(())
}
/// Update timestamp in a row in a special service table to check
/// that we can actually write some data in this particular timeline.
#[instrument(skip_all)]
pub async fn check_writability(compute: &ComputeNode) -> Result<()> {
// Connect to the database.
let (client, connection) = tokio_postgres::connect(compute.connstr.as_str(), NoTls).await?;
if client.is_closed() {
return Err(anyhow!("connection to postgres closed"));
}
// The connection object performs the actual communication with the database,
// so spawn it off to run on its own.
tokio::spawn(async move {
if let Err(e) = connection.await {
error!("connection error: {}", e);
}
});
let query = "
INSERT INTO health_check VALUES (1, now())
ON CONFLICT (id) DO UPDATE
SET updated_at = now();";
let result = client
.simple_query("UPDATE health_check SET updated_at = now() WHERE id = 1;")
.await?;
match client.simple_query(query).await {
Result::Ok(result) => {
if result.len() != 1 {
return Err(anyhow::anyhow!(
"expected 1 query results, but got {}",
result.len()
));
}
}
Err(err) => {
if let Some(state) = err.code() {
if state == &tokio_postgres::error::SqlState::DISK_FULL {
warn!("Tenant disk is full");
return Ok(());
}
}
return Err(err.into());
}
if result.len() != 1 {
return Err(anyhow!("statement can't be executed"));
}
Ok(())
}

File diff suppressed because it is too large Load Diff

View File

@@ -5,9 +5,8 @@ use std::path::Path;
use anyhow::Result;
use crate::pg_helpers::escape_conf_value;
use crate::pg_helpers::PgOptionsSerialize;
use compute_api::spec::{ComputeMode, ComputeSpec};
use crate::spec::ComputeSpec;
/// Check that `line` is inside a text file and put it there if it is not.
/// Create file if it doesn't exist.
@@ -33,65 +32,20 @@ pub fn line_in_file(path: &Path, line: &str) -> Result<bool> {
}
/// Create or completely rewrite configuration file specified by `path`
pub fn write_postgres_conf(
path: &Path,
spec: &ComputeSpec,
extension_server_port: Option<u16>,
) -> Result<()> {
pub fn write_postgres_conf(path: &Path, spec: &ComputeSpec) -> Result<()> {
// File::create() destroys the file content if it exists.
let mut file = File::create(path)?;
let mut postgres_conf = File::create(path)?;
// Write the postgresql.conf content from the spec file as is.
if let Some(conf) = &spec.cluster.postgresql_conf {
writeln!(file, "{}", conf)?;
}
// Add options for connecting to storage
writeln!(file, "# Neon storage settings")?;
if let Some(s) = &spec.pageserver_connstring {
writeln!(file, "neon.pageserver_connstring={}", escape_conf_value(s))?;
}
if !spec.safekeeper_connstrings.is_empty() {
writeln!(
file,
"neon.safekeepers={}",
escape_conf_value(&spec.safekeeper_connstrings.join(","))
)?;
}
if let Some(s) = &spec.tenant_id {
writeln!(file, "neon.tenant_id={}", escape_conf_value(&s.to_string()))?;
}
if let Some(s) = &spec.timeline_id {
writeln!(
file,
"neon.timeline_id={}",
escape_conf_value(&s.to_string())
)?;
}
match spec.mode {
ComputeMode::Primary => {}
ComputeMode::Static(lsn) => {
// hot_standby is 'on' by default, but let's be explicit
writeln!(file, "hot_standby=on")?;
writeln!(file, "recovery_target_lsn='{lsn}'")?;
}
ComputeMode::Replica => {
// hot_standby is 'on' by default, but let's be explicit
writeln!(file, "hot_standby=on")?;
}
}
// If there are any extra options in the 'settings' field, append those
if spec.cluster.settings.is_some() {
writeln!(file, "# Managed by compute_ctl: begin")?;
write!(file, "{}", spec.cluster.settings.as_pg_settings())?;
writeln!(file, "# Managed by compute_ctl: end")?;
}
if let Some(port) = extension_server_port {
writeln!(file, "neon.extension_server_port={}", port)?;
}
write_auto_managed_block(&mut postgres_conf, &spec.cluster.settings.as_pg_settings())?;
Ok(())
}
// Write Postgres config block wrapped with generated comment section
fn write_auto_managed_block(file: &mut File, buf: &str) -> Result<()> {
writeln!(file, "# Managed by compute_ctl: begin")?;
writeln!(file, "{}", buf)?;
writeln!(file, "# Managed by compute_ctl: end")?;
Ok(())
}

View File

@@ -1,54 +0,0 @@
use std::sync::Arc;
use std::thread;
use tracing::{error, info, instrument};
use compute_api::responses::ComputeStatus;
use crate::compute::ComputeNode;
#[instrument(skip_all)]
fn configurator_main_loop(compute: &Arc<ComputeNode>) {
info!("waiting for reconfiguration requests");
loop {
let state = compute.state.lock().unwrap();
let mut state = compute.state_changed.wait(state).unwrap();
if state.status == ComputeStatus::ConfigurationPending {
info!("got configuration request");
state.status = ComputeStatus::Configuration;
compute.state_changed.notify_all();
drop(state);
let mut new_status = ComputeStatus::Failed;
if let Err(e) = compute.reconfigure() {
error!("could not configure compute node: {}", e);
} else {
new_status = ComputeStatus::Running;
info!("compute node configured");
}
// XXX: used to test that API is blocking
// std::thread::sleep(std::time::Duration::from_millis(10000));
compute.set_status(new_status);
} else if state.status == ComputeStatus::Failed {
info!("compute node is now in Failed state, exiting");
break;
} else {
info!("woken up for compute status: {:?}, sleeping", state.status);
}
}
}
pub fn launch_configurator(compute: &Arc<ComputeNode>) -> thread::JoinHandle<()> {
let compute = Arc::clone(compute);
thread::Builder::new()
.name("compute-configurator".into())
.spawn(move || {
configurator_main_loop(&compute);
info!("configurator thread is exited");
})
.expect("cannot launch configurator thread")
}

View File

@@ -1,289 +0,0 @@
// Download extension files from the extension store
// and put them in the right place in the postgres directory (share / lib)
/*
The layout of the S3 bucket is as follows:
5615610098 // this is an extension build number
├── v14
│   ├── extensions
│   │   ├── anon.tar.zst
│   │   └── embedding.tar.zst
│   └── ext_index.json
└── v15
├── extensions
│   ├── anon.tar.zst
│   └── embedding.tar.zst
└── ext_index.json
5615261079
├── v14
│   ├── extensions
│   │   └── anon.tar.zst
│   └── ext_index.json
└── v15
├── extensions
│   └── anon.tar.zst
└── ext_index.json
5623261088
├── v14
│   ├── extensions
│   │   └── embedding.tar.zst
│   └── ext_index.json
└── v15
├── extensions
│   └── embedding.tar.zst
└── ext_index.json
Note that build number cannot be part of prefix because we might need extensions
from other build numbers.
ext_index.json stores the control files and location of extension archives
It also stores a list of public extensions and a library_index
We don't need to duplicate extension.tar.zst files.
We only need to upload a new one if it is updated.
(Although currently we just upload every time anyways, hopefully will change
this sometime)
*access* is controlled by spec
More specifically, here is an example ext_index.json
{
"public_extensions": [
"anon",
"pg_buffercache"
],
"library_index": {
"anon": "anon",
"pg_buffercache": "pg_buffercache"
},
"extension_data": {
"pg_buffercache": {
"control_data": {
"pg_buffercache.control": "# pg_buffercache extension \ncomment = 'examine the shared buffer cache' \ndefault_version = '1.3' \nmodule_pathname = '$libdir/pg_buffercache' \nrelocatable = true \ntrusted=true"
},
"archive_path": "5670669815/v14/extensions/pg_buffercache.tar.zst"
},
"anon": {
"control_data": {
"anon.control": "# PostgreSQL Anonymizer (anon) extension \ncomment = 'Data anonymization tools' \ndefault_version = '1.1.0' \ndirectory='extension/anon' \nrelocatable = false \nrequires = 'pgcrypto' \nsuperuser = false \nmodule_pathname = '$libdir/anon' \ntrusted = true \n"
},
"archive_path": "5670669815/v14/extensions/anon.tar.zst"
}
}
}
*/
use anyhow::Context;
use anyhow::{self, Result};
use compute_api::spec::RemoteExtSpec;
use regex::Regex;
use remote_storage::*;
use serde_json;
use std::io::Read;
use std::num::{NonZeroU32, NonZeroUsize};
use std::path::Path;
use std::str;
use tar::Archive;
use tokio::io::AsyncReadExt;
use tracing::info;
use tracing::log::warn;
use zstd::stream::read::Decoder;
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`
let pgconfig = pgbin
.strip_suffix("postgres")
.expect("bad pgbin")
.to_owned()
+ "/pg_config";
let config_output = std::process::Command::new(pgconfig)
.arg(argument)
.output()
.expect("pg_config error");
std::str::from_utf8(&config_output.stdout)
.expect("pg_config error")
.trim()
.to_string()
}
pub fn get_pg_version(pgbin: &str) -> String {
// pg_config --version returns a (platform specific) human readable string
// such as "PostgreSQL 15.4". We parse this to v14/v15/v16 etc.
let human_version = get_pg_config("--version", pgbin);
return parse_pg_version(&human_version).to_string();
}
fn parse_pg_version(human_version: &str) -> &str {
// Normal releases have version strings like "PostgreSQL 15.4". But there
// are also pre-release versions like "PostgreSQL 17devel" or "PostgreSQL
// 16beta2" or "PostgreSQL 17rc1". And with the --with-extra-version
// configure option, you can tack any string to the version number,
// e.g. "PostgreSQL 15.4foobar".
match Regex::new(r"^PostgreSQL (?<major>\d+).+")
.unwrap()
.captures(human_version)
{
Some(captures) if captures.len() == 2 => match &captures["major"] {
"14" => return "v14",
"15" => return "v15",
"16" => return "v16",
_ => {}
},
_ => {}
}
panic!("Unsuported postgres version {human_version}");
}
#[cfg(test)]
mod tests {
use super::parse_pg_version;
#[test]
fn test_parse_pg_version() {
assert_eq!(parse_pg_version("PostgreSQL 15.4"), "v15");
assert_eq!(parse_pg_version("PostgreSQL 15.14"), "v15");
assert_eq!(
parse_pg_version("PostgreSQL 15.4 (Ubuntu 15.4-0ubuntu0.23.04.1)"),
"v15"
);
assert_eq!(parse_pg_version("PostgreSQL 14.15"), "v14");
assert_eq!(parse_pg_version("PostgreSQL 14.0"), "v14");
assert_eq!(
parse_pg_version("PostgreSQL 14.9 (Debian 14.9-1.pgdg120+1"),
"v14"
);
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]
#[should_panic]
fn test_parse_pg_unsupported_version() {
parse_pg_version("PostgreSQL 13.14");
}
#[test]
#[should_panic]
fn test_parse_pg_incorrect_version_format() {
parse_pg_version("PostgreSQL 14");
}
}
// download the archive for a given extension,
// unzip it, and place files in the appropriate locations (share/lib)
pub async fn download_extension(
ext_name: &str,
ext_path: &RemotePath,
remote_storage: &GenericRemoteStorage,
pgbin: &str,
) -> Result<u64> {
info!("Download extension {:?} from {:?}", ext_name, ext_path);
let mut download = remote_storage.download(ext_path).await?;
let mut download_buffer = Vec::new();
download
.download_stream
.read_to_end(&mut download_buffer)
.await?;
let download_size = download_buffer.len() as u64;
// it's unclear whether it is more performant to decompress into memory or not
// TODO: decompressing into memory can be avoided
let mut decoder = Decoder::new(download_buffer.as_slice())?;
let mut decompress_buffer = Vec::new();
decoder.read_to_end(&mut decompress_buffer)?;
let mut archive = Archive::new(decompress_buffer.as_slice());
let unzip_dest = pgbin
.strip_suffix("/bin/postgres")
.expect("bad pgbin")
.to_string()
+ "/download_extensions";
archive.unpack(&unzip_dest)?;
info!("Download + unzip {:?} completed successfully", &ext_path);
let sharedir_paths = (
unzip_dest.to_string() + "/share/extension",
Path::new(&get_pg_config("--sharedir", pgbin)).join("extension"),
);
let libdir_paths = (
unzip_dest.to_string() + "/lib",
Path::new(&get_pg_config("--pkglibdir", pgbin)).to_path_buf(),
);
// move contents of the libdir / sharedir in unzipped archive to the correct local paths
for paths in [sharedir_paths, libdir_paths] {
let (zip_dir, real_dir) = paths;
info!("mv {zip_dir:?}/* {real_dir:?}");
for file in std::fs::read_dir(zip_dir)? {
let old_file = file?.path();
let new_file =
Path::new(&real_dir).join(old_file.file_name().context("error parsing file")?);
info!("moving {old_file:?} to {new_file:?}");
// extension download failed: Directory not empty (os error 39)
match std::fs::rename(old_file, new_file) {
Ok(()) => info!("move succeeded"),
Err(e) => {
warn!("move failed, probably because the extension already exists: {e}")
}
}
}
}
info!("done moving extension {ext_name}");
Ok(download_size)
}
// Create extension control files from spec
pub fn create_control_files(remote_extensions: &RemoteExtSpec, pgbin: &str) {
let local_sharedir = Path::new(&get_pg_config("--sharedir", pgbin)).join("extension");
for (ext_name, ext_data) in remote_extensions.extension_data.iter() {
// Check if extension is present in public or custom.
// If not, then it is not allowed to be used by this compute.
if let Some(public_extensions) = &remote_extensions.public_extensions {
if !public_extensions.contains(ext_name) {
if let Some(custom_extensions) = &remote_extensions.custom_extensions {
if !custom_extensions.contains(ext_name) {
continue; // skip this extension, it is not allowed
}
}
}
}
for (control_name, control_content) in &ext_data.control_data {
let control_path = local_sharedir.join(control_name);
if !control_path.exists() {
info!("writing file {:?}{:?}", control_path, control_content);
std::fs::write(control_path, control_content).unwrap();
} else {
warn!("control file {:?} exists both locally and remotely. ignoring the remote version.", control_path);
}
}
}
}
// This function initializes the necessary structs to use remote storage
pub fn init_remote_storage(remote_ext_config: &str) -> anyhow::Result<GenericRemoteStorage> {
#[derive(Debug, serde::Deserialize)]
struct RemoteExtJson {
bucket: String,
region: String,
endpoint: Option<String>,
prefix: Option<String>,
}
let remote_ext_json = serde_json::from_str::<RemoteExtJson>(remote_ext_config)?;
let config = S3Config {
bucket_name: remote_ext_json.bucket,
bucket_region: remote_ext_json.region,
prefix_in_bucket: remote_ext_json.prefix,
endpoint: remote_ext_json.endpoint,
concurrency_limit: NonZeroUsize::new(100).expect("100 != 0"),
max_keys_per_list_response: None,
};
let config = RemoteStorageConfig {
max_concurrent_syncs: NonZeroUsize::new(100).expect("100 != 0"),
max_sync_errors: NonZeroU32::new(100).expect("100 != 0"),
storage: RemoteStorageKind::AwsS3(config),
};
GenericRemoteStorage::from_config(&config)
}

View File

@@ -1,202 +1,39 @@
use std::convert::Infallible;
use std::net::IpAddr;
use std::net::Ipv6Addr;
use std::net::SocketAddr;
use std::sync::Arc;
use std::thread;
use crate::compute::{ComputeNode, ComputeState, ParsedSpec};
use compute_api::requests::ConfigurationRequest;
use compute_api::responses::{ComputeStatus, ComputeStatusResponse, GenericAPIError};
use anyhow::Result;
use hyper::service::{make_service_fn, service_fn};
use hyper::{Body, Method, Request, Response, Server, StatusCode};
use num_cpus;
use serde_json;
use tokio::task;
use tracing::{error, info, warn};
use tracing_utils::http::OtelName;
use tracing::{error, info};
fn status_response_from_state(state: &ComputeState) -> ComputeStatusResponse {
ComputeStatusResponse {
start_time: state.start_time,
tenant: state
.pspec
.as_ref()
.map(|pspec| pspec.tenant_id.to_string()),
timeline: state
.pspec
.as_ref()
.map(|pspec| pspec.timeline_id.to_string()),
status: state.status,
last_active: state.last_active,
error: state.error.clone(),
}
}
use crate::compute::ComputeNode;
// Service function to handle all available routes.
async fn routes(req: Request<Body>, compute: &Arc<ComputeNode>) -> Response<Body> {
//
// NOTE: The URI path is currently included in traces. That's OK because
// it doesn't contain any variable parts or sensitive information. But
// please keep that in mind if you change the routing here.
//
async fn routes(req: Request<Body>, compute: Arc<ComputeNode>) -> Response<Body> {
match (req.method(), req.uri().path()) {
// Serialized compute state.
(&Method::GET, "/status") => {
info!("serving /status GET request");
let state = compute.state.lock().unwrap();
let status_response = status_response_from_state(&state);
Response::new(Body::from(serde_json::to_string(&status_response).unwrap()))
let state = compute.state.read().unwrap();
Response::new(Body::from(serde_json::to_string(&*state).unwrap()))
}
// Startup metrics in JSON format. Keep /metrics reserved for a possible
// future use for Prometheus metrics format.
(&Method::GET, "/metrics.json") => {
info!("serving /metrics.json GET request");
let metrics = compute.state.lock().unwrap().metrics.clone();
Response::new(Body::from(serde_json::to_string(&metrics).unwrap()))
}
// Collect Postgres current usage insights
(&Method::GET, "/insights") => {
info!("serving /insights GET request");
let status = compute.get_status();
if status != ComputeStatus::Running {
let msg = format!("compute is not running, current status: {:?}", status);
error!(msg);
return Response::new(Body::from(msg));
}
let insights = compute.collect_insights().await;
Response::new(Body::from(insights))
Response::new(Body::from(serde_json::to_string(&compute.metrics).unwrap()))
}
(&Method::POST, "/check_writability") => {
info!("serving /check_writability POST request");
let status = compute.get_status();
if status != ComputeStatus::Running {
let msg = format!(
"invalid compute status for check_writability request: {:?}",
status
);
error!(msg);
return Response::new(Body::from(msg));
}
let res = crate::checker::check_writability(compute).await;
let res = crate::checker::check_writability(&compute).await;
match res {
Ok(_) => Response::new(Body::from("true")),
Err(e) => {
error!("check_writability failed: {}", e);
Response::new(Body::from(e.to_string()))
}
}
}
(&Method::GET, "/info") => {
let num_cpus = num_cpus::get_physical();
info!("serving /info GET request. num_cpus: {}", num_cpus);
Response::new(Body::from(
serde_json::json!({
"num_cpus": num_cpus,
})
.to_string(),
))
}
// Accept spec in JSON format and request compute configuration. If
// anything goes wrong after we set the compute status to `ConfigurationPending`
// and update compute state with new spec, we basically leave compute
// in the potentially wrong state. That said, it's control-plane's
// responsibility to watch compute state after reconfiguration request
// and to clean restart in case of errors.
(&Method::POST, "/configure") => {
info!("serving /configure POST request");
match handle_configure_request(req, compute).await {
Ok(msg) => Response::new(Body::from(msg)),
Err((msg, code)) => {
error!("error handling /configure request: {msg}");
render_json_error(&msg, code)
}
}
}
// download extension files from S3 on demand
(&Method::POST, route) if route.starts_with("/extension_server/") => {
info!("serving {:?} POST request", route);
info!("req.uri {:?}", req.uri());
// don't even try to download extensions
// if no remote storage is configured
if compute.ext_remote_storage.is_none() {
info!("no extensions remote storage configured");
let mut resp = Response::new(Body::from("no remote storage configured"));
*resp.status_mut() = StatusCode::INTERNAL_SERVER_ERROR;
return resp;
}
let mut is_library = false;
if let Some(params) = req.uri().query() {
info!("serving {:?} POST request with params: {}", route, params);
if params == "is_library=true" {
is_library = true;
} else {
let mut resp = Response::new(Body::from("Wrong request parameters"));
*resp.status_mut() = StatusCode::BAD_REQUEST;
return resp;
}
}
let filename = route.split('/').last().unwrap().to_string();
info!("serving /extension_server POST request, filename: {filename:?} is_library: {is_library}");
// get ext_name and path from spec
// don't lock compute_state for too long
let ext = {
let compute_state = compute.state.lock().unwrap();
let pspec = compute_state.pspec.as_ref().expect("spec must be set");
let spec = &pspec.spec;
// debug only
info!("spec: {:?}", spec);
let remote_extensions = match spec.remote_extensions.as_ref() {
Some(r) => r,
None => {
info!("no remote extensions spec was provided");
let mut resp = Response::new(Body::from("no remote storage configured"));
*resp.status_mut() = StatusCode::INTERNAL_SERVER_ERROR;
return resp;
}
};
remote_extensions.get_ext(
&filename,
is_library,
&compute.build_tag,
&compute.pgversion,
)
};
match ext {
Ok((ext_name, ext_path)) => {
match compute.download_extension(ext_name, ext_path).await {
Ok(_) => Response::new(Body::from("OK")),
Err(e) => {
error!("extension download failed: {}", e);
let mut resp = Response::new(Body::from(e.to_string()));
*resp.status_mut() = StatusCode::INTERNAL_SERVER_ERROR;
resp
}
}
}
Err(e) => {
warn!("extension download failed to find extension: {}", e);
let mut resp = Response::new(Body::from("failed to find file"));
*resp.status_mut() = StatusCode::INTERNAL_SERVER_ERROR;
resp
}
Err(e) => Response::new(Body::from(e.to_string())),
}
}
@@ -209,119 +46,17 @@ async fn routes(req: Request<Body>, compute: &Arc<ComputeNode>) -> Response<Body
}
}
async fn handle_configure_request(
req: Request<Body>,
compute: &Arc<ComputeNode>,
) -> Result<String, (String, StatusCode)> {
if !compute.live_config_allowed {
return Err((
"live configuration is not allowed for this compute node".to_string(),
StatusCode::PRECONDITION_FAILED,
));
}
let body_bytes = hyper::body::to_bytes(req.into_body()).await.unwrap();
let spec_raw = String::from_utf8(body_bytes.to_vec()).unwrap();
if let Ok(request) = serde_json::from_str::<ConfigurationRequest>(&spec_raw) {
let spec = request.spec;
let parsed_spec = match ParsedSpec::try_from(spec) {
Ok(ps) => ps,
Err(msg) => return Err((msg, StatusCode::PRECONDITION_FAILED)),
};
// XXX: wrap state update under lock in code blocks. Otherwise,
// we will try to `Send` `mut state` into the spawned thread
// bellow, which will cause error:
// ```
// error: future cannot be sent between threads safely
// ```
{
let mut state = compute.state.lock().unwrap();
if state.status != ComputeStatus::Empty && state.status != ComputeStatus::Running {
let msg = format!(
"invalid compute status for configuration request: {:?}",
state.status.clone()
);
return Err((msg, StatusCode::PRECONDITION_FAILED));
}
state.pspec = Some(parsed_spec);
state.status = ComputeStatus::ConfigurationPending;
compute.state_changed.notify_all();
drop(state);
info!("set new spec and notified waiters");
}
// Spawn a blocking thread to wait for compute to become Running.
// This is needed to do not block the main pool of workers and
// be able to serve other requests while some particular request
// is waiting for compute to finish configuration.
let c = compute.clone();
task::spawn_blocking(move || {
let mut state = c.state.lock().unwrap();
while state.status != ComputeStatus::Running {
state = c.state_changed.wait(state).unwrap();
info!(
"waiting for compute to become Running, current status: {:?}",
state.status
);
if state.status == ComputeStatus::Failed {
let err = state.error.as_ref().map_or("unknown error", |x| x);
let msg = format!("compute configuration failed: {:?}", err);
return Err((msg, StatusCode::INTERNAL_SERVER_ERROR));
}
}
Ok(())
})
.await
.unwrap()?;
// Return current compute state if everything went well.
let state = compute.state.lock().unwrap().clone();
let status_response = status_response_from_state(&state);
Ok(serde_json::to_string(&status_response).unwrap())
} else {
Err(("invalid spec".to_string(), StatusCode::BAD_REQUEST))
}
}
fn render_json_error(e: &str, status: StatusCode) -> Response<Body> {
let error = GenericAPIError {
error: e.to_string(),
};
Response::builder()
.status(status)
.body(Body::from(serde_json::to_string(&error).unwrap()))
.unwrap()
}
// Main Hyper HTTP server function that runs it and blocks waiting on it forever.
#[tokio::main]
async fn serve(port: u16, state: Arc<ComputeNode>) {
// this usually binds to both IPv4 and IPv6 on linux
// see e.g. https://github.com/rust-lang/rust/pull/34440
let addr = SocketAddr::new(IpAddr::from(Ipv6Addr::UNSPECIFIED), port);
async fn serve(state: Arc<ComputeNode>) {
let addr = SocketAddr::from(([0, 0, 0, 0], 3080));
let make_service = make_service_fn(move |_conn| {
let state = state.clone();
async move {
Ok::<_, Infallible>(service_fn(move |req: Request<Body>| {
let state = state.clone();
async move {
Ok::<_, Infallible>(
// NOTE: We include the URI path in the string. It
// doesn't contain any variable parts or sensitive
// information in this API.
tracing_utils::http::tracing_handler(
req,
|req| routes(req, &state),
OtelName::UriPath,
)
.await,
)
}
async move { Ok::<_, Infallible>(routes(req, state).await) }
}))
}
});
@@ -337,10 +72,10 @@ async fn serve(port: u16, state: Arc<ComputeNode>) {
}
/// Launch a separate Hyper HTTP API server thread and return its `JoinHandle`.
pub fn launch_http_server(port: u16, state: &Arc<ComputeNode>) -> Result<thread::JoinHandle<()>> {
pub fn launch_http_server(state: &Arc<ComputeNode>) -> Result<thread::JoinHandle<()>> {
let state = Arc::clone(state);
Ok(thread::Builder::new()
.name("http-endpoint".into())
.spawn(move || serve(port, state))?)
.spawn(move || serve(state))?)
}

View File

@@ -10,12 +10,12 @@ paths:
/status:
get:
tags:
- Info
summary: Get compute node internal status.
- "info"
summary: Get compute node internal status
description: ""
operationId: getComputeStatus
responses:
200:
"200":
description: ComputeState
content:
application/json:
@@ -25,149 +25,35 @@ paths:
/metrics.json:
get:
tags:
- Info
summary: Get compute node startup metrics in JSON format.
- "info"
summary: Get compute node startup metrics in JSON format
description: ""
operationId: getComputeMetricsJSON
responses:
200:
"200":
description: ComputeMetrics
content:
application/json:
schema:
$ref: "#/components/schemas/ComputeMetrics"
/insights:
get:
tags:
- Info
summary: Get current compute insights in JSON format.
description: |
Note, that this doesn't include any historical data.
operationId: getComputeInsights
responses:
200:
description: Compute insights
content:
application/json:
schema:
$ref: "#/components/schemas/ComputeInsights"
/info:
get:
tags:
- Info
summary: Get info about the compute pod / VM.
description: ""
operationId: getInfo
responses:
200:
description: Info
content:
application/json:
schema:
$ref: "#/components/schemas/Info"
/check_writability:
post:
tags:
- Check
summary: Check that we can write new data on this compute.
- "check"
summary: Check that we can write new data on this compute
description: ""
operationId: checkComputeWritability
responses:
200:
"200":
description: Check result
content:
text/plain:
schema:
type: string
description: Error text or 'true' if check passed.
description: Error text or 'true' if check passed
example: "true"
/configure:
post:
tags:
- Configure
summary: Perform compute node configuration.
description: |
This is a blocking API endpoint, i.e. it blocks waiting until
compute is finished configuration and is in `Running` state.
Optional non-blocking mode could be added later.
operationId: configureCompute
requestBody:
description: Configuration request.
required: true
content:
application/json:
schema:
type: object
required:
- spec
properties:
spec:
# XXX: I don't want to explain current spec in the OpenAPI format,
# as it could be changed really soon. Consider doing it later.
type: object
responses:
200:
description: Compute configuration finished.
content:
application/json:
schema:
$ref: "#/components/schemas/ComputeState"
400:
description: Provided spec is invalid.
content:
application/json:
schema:
$ref: "#/components/schemas/GenericError"
412:
description: |
It's not possible to do live-configuration of the compute.
It's either in the wrong state, or compute doesn't use pull
mode of configuration.
content:
application/json:
schema:
$ref: "#/components/schemas/GenericError"
500:
description: |
Compute configuration request was processed, but error
occurred. Compute will likely shutdown soon.
content:
application/json:
schema:
$ref: "#/components/schemas/GenericError"
/extension_server:
post:
tags:
- Extension
summary: Download extension from S3 to local folder.
description: ""
operationId: downloadExtension
responses:
200:
description: Extension downloaded
content:
text/plain:
schema:
type: string
description: Error text or 'OK' if download succeeded.
example: "OK"
400:
description: Request is invalid.
content:
application/json:
schema:
$ref: "#/components/schemas/GenericError"
500:
description: Extension download request failed.
content:
application/json:
schema:
$ref: "#/components/schemas/GenericError"
components:
securitySchemes:
JWT:
@@ -178,16 +64,13 @@ components:
schemas:
ComputeMetrics:
type: object
description: Compute startup metrics.
description: Compute startup metrics
required:
- wait_for_spec_ms
- sync_safekeepers_ms
- basebackup_ms
- config_ms
- total_startup_ms
properties:
wait_for_spec_ms:
type: integer
sync_safekeepers_ms:
type: integer
basebackup_ms:
@@ -197,80 +80,28 @@ components:
total_startup_ms:
type: integer
Info:
type: object
description: Information about VM/Pod.
required:
- num_cpus
properties:
num_cpus:
type: integer
ComputeState:
type: object
required:
- start_time
- status
- last_active
properties:
start_time:
type: string
description: |
Time when compute was started. If initially compute was started in the `empty`
state and then provided with valid spec, `start_time` will be reset to the
moment, when spec was received.
example: "2022-10-12T07:20:50.52Z"
status:
$ref: '#/components/schemas/ComputeStatus'
last_active:
type: string
description: |
The last detected compute activity timestamp in UTC and RFC3339 format.
It could be empty if compute was never used by user since start.
description: The last detected compute activity timestamp in UTC and RFC3339 format
example: "2022-10-12T07:20:50.52Z"
error:
type: string
description: Text of the error during compute startup or reconfiguration, if any.
example: ""
tenant:
type: string
description: Identifier of the current tenant served by compute node, if any.
example: c9269c359e9a199fad1ea0981246a78f
timeline:
type: string
description: Identifier of the current timeline served by compute node, if any.
example: ece7de74d4b8cbe5433a68ce4d1b97b4
ComputeInsights:
type: object
properties:
pg_stat_statements:
description: Contains raw output from pg_stat_statements in JSON format.
type: array
items:
type: object
description: Text of the error during compute startup, if any
ComputeStatus:
type: string
enum:
- empty
- init
- failed
- running
- configuration_pending
- configuration
example: running
#
# Errors
#
GenericError:
type: object
required:
- error
properties:
error:
type: string
security:
- JWT: []

View File

@@ -0,0 +1,50 @@
use std::path::Path;
use std::process;
use std::thread;
use std::time::Duration;
use tracing::{info, warn};
use anyhow::{Context, Result};
const VM_INFORMANT_PATH: &str = "/bin/vm-informant";
const RESTART_INFORMANT_AFTER_MILLIS: u64 = 5000;
/// Launch a thread to start the VM informant if it's present (and restart, on failure)
pub fn spawn_vm_informant_if_present() -> Result<Option<thread::JoinHandle<()>>> {
let exists = Path::new(VM_INFORMANT_PATH)
.try_exists()
.context("could not check if path exists")?;
if !exists {
return Ok(None);
}
Ok(Some(
thread::Builder::new()
.name("run-vm-informant".into())
.spawn(move || run_informant())?,
))
}
fn run_informant() -> ! {
let restart_wait = Duration::from_millis(RESTART_INFORMANT_AFTER_MILLIS);
info!("starting VM informant");
loop {
let mut cmd = process::Command::new(VM_INFORMANT_PATH);
// Block on subprocess:
let result = cmd.status();
match result {
Err(e) => warn!("failed to run VM informant at {VM_INFORMANT_PATH:?}: {e}"),
Ok(status) if !status.success() => {
warn!("{VM_INFORMANT_PATH} exited with code {status:?}, retrying")
}
Ok(_) => info!("{VM_INFORMANT_PATH} ended gracefully (unexpectedly). Retrying"),
}
// Wait before retrying
thread::sleep(restart_wait);
}
}

View File

@@ -4,14 +4,12 @@
//!
pub mod checker;
pub mod config;
pub mod configurator;
pub mod http;
#[macro_use]
pub mod logger;
pub mod compute;
pub mod extension_server;
pub mod informant;
pub mod monitor;
pub mod params;
pub mod pg_helpers;
pub mod spec;
pub mod sync_sk;

View File

@@ -1,40 +1,21 @@
use tracing_opentelemetry::OpenTelemetryLayer;
use anyhow::Result;
use tracing_subscriber::layer::SubscriberExt;
use tracing_subscriber::prelude::*;
/// Initialize logging to stderr, and OpenTelemetry tracing and exporter.
///
/// Logging is configured using either `default_log_level` or
/// Initialize `env_logger` using either `default_level` or
/// `RUST_LOG` environment variable as default log level.
///
/// OpenTelemetry is configured with OTLP/HTTP exporter. It picks up
/// configuration from environment variables. For example, to change the destination,
/// set `OTEL_EXPORTER_OTLP_ENDPOINT=http://jaeger:4318`. See
/// `tracing-utils` package description.
///
pub fn init_tracing_and_logging(default_log_level: &str) -> anyhow::Result<()> {
// Initialize Logging
pub fn init_logger(default_level: &str) -> Result<()> {
let env_filter = tracing_subscriber::EnvFilter::try_from_default_env()
.unwrap_or_else(|_| tracing_subscriber::EnvFilter::new(default_log_level));
.unwrap_or_else(|_| tracing_subscriber::EnvFilter::new(default_level));
let fmt_layer = tracing_subscriber::fmt::layer()
.with_ansi(false)
.with_target(false)
.with_writer(std::io::stderr);
// Initialize OpenTelemetry
let otlp_layer =
tracing_utils::init_tracing_without_runtime("compute_ctl").map(OpenTelemetryLayer::new);
// Put it all together
tracing_subscriber::registry()
.with(env_filter)
.with(otlp_layer)
.with(fmt_layer)
.init();
tracing::info!("logging and tracing started");
utils::logging::replace_panic_hook_with_tracing_panic_hook().forget();
Ok(())
}

View File

@@ -1,6 +1,7 @@
use std::sync::Arc;
use std::{thread, time};
use anyhow::Result;
use chrono::{DateTime, Utc};
use postgres::{Client, NoTls};
use tracing::{debug, info};
@@ -45,7 +46,7 @@ fn watch_compute_activity(compute: &ComputeNode) {
AND usename != 'cloud_admin';", // XXX: find a better way to filter other monitors?
&[],
);
let mut last_active = compute.state.lock().unwrap().last_active;
let mut last_active = compute.state.read().unwrap().last_active;
if let Ok(backs) = backends {
let mut idle_backs: Vec<DateTime<Utc>> = vec![];
@@ -73,7 +74,7 @@ fn watch_compute_activity(compute: &ComputeNode) {
// Found non-idle backend, so the last activity is NOW.
// Save it and exit the for loop. Also clear the idle backend
// `state_change` timestamps array as it doesn't matter now.
last_active = Some(Utc::now());
last_active = Utc::now();
idle_backs.clear();
break;
}
@@ -81,16 +82,15 @@ fn watch_compute_activity(compute: &ComputeNode) {
// Get idle backend `state_change` with the max timestamp.
if let Some(last) = idle_backs.iter().max() {
last_active = Some(*last);
last_active = *last;
}
}
// Update the last activity in the shared state if we got a more recent one.
let mut state = compute.state.lock().unwrap();
// NB: `Some(<DateTime>)` is always greater than `None`.
let mut state = compute.state.write().unwrap();
if last_active > state.last_active {
state.last_active = last_active;
debug!("set the last compute activity time to: {:?}", last_active);
debug!("set the last compute activity time to: {}", last_active);
}
}
Err(e) => {
@@ -104,11 +104,10 @@ fn watch_compute_activity(compute: &ComputeNode) {
}
/// Launch a separate compute monitor thread and return its `JoinHandle`.
pub fn launch_monitor(state: &Arc<ComputeNode>) -> thread::JoinHandle<()> {
pub fn launch_monitor(state: &Arc<ComputeNode>) -> Result<thread::JoinHandle<()>> {
let state = Arc::clone(state);
thread::Builder::new()
Ok(thread::Builder::new()
.name("compute-monitor".into())
.spawn(move || watch_compute_activity(&state))
.expect("cannot launch compute monitor thread")
.spawn(move || watch_compute_activity(&state))?)
}

View File

@@ -6,4 +6,4 @@ pub const DEFAULT_LOG_LEVEL: &str = "info";
// https://www.postgresql.org/docs/15/auth-password.html
//
// So it's safe to set md5 here, as `control-plane` anyway uses SCRAM for all roles.
pub const PG_HBA_ALL_MD5: &str = "host\tall\t\tall\t\tall\t\tmd5";
pub const PG_HBA_ALL_MD5: &str = "host\tall\t\tall\t\t0.0.0.0/0\t\tmd5";

View File

@@ -10,45 +10,49 @@ use std::time::{Duration, Instant};
use anyhow::{bail, Result};
use notify::{RecursiveMode, Watcher};
use postgres::{Client, Transaction};
use serde::Deserialize;
use tracing::{debug, instrument};
use compute_api::spec::{Database, GenericOption, GenericOptions, PgIdent, Role};
const POSTGRES_WAIT_TIMEOUT: Duration = Duration::from_millis(60 * 1000); // milliseconds
/// Escape a string for including it in a SQL literal. Wrapping the result
/// with `E'{}'` or `'{}'` is not required, as it returns a ready-to-use
/// SQL string literal, e.g. `'db'''` or `E'db\\'`.
/// See <https://github.com/postgres/postgres/blob/da98d005cdbcd45af563d0c4ac86d0e9772cd15f/src/backend/utils/adt/quote.c#L47>
/// for the original implementation.
pub fn escape_literal(s: &str) -> String {
let res = s.replace('\'', "''").replace('\\', "\\\\");
if res.contains('\\') {
format!("E'{}'", res)
} else {
format!("'{}'", res)
}
/// Rust representation of Postgres role info with only those fields
/// that matter for us.
#[derive(Clone, Deserialize)]
pub struct Role {
pub name: PgIdent,
pub encrypted_password: Option<String>,
pub options: GenericOptions,
}
/// Escape a string so that it can be used in postgresql.conf. Wrapping the result
/// 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)
/// Rust representation of Postgres database info with only those fields
/// that matter for us.
#[derive(Clone, Deserialize)]
pub struct Database {
pub name: PgIdent,
pub owner: PgIdent,
pub options: GenericOptions,
}
trait GenericOptionExt {
fn to_pg_option(&self) -> String;
fn to_pg_setting(&self) -> String;
/// Common type representing both SQL statement params with or without value,
/// like `LOGIN` or `OWNER username` in the `CREATE/ALTER ROLE`, and config
/// options like `wal_level = logical`.
#[derive(Clone, Deserialize)]
pub struct GenericOption {
pub name: String,
pub value: Option<String>,
pub vartype: String,
}
impl GenericOptionExt for GenericOption {
/// Optional collection of `GenericOption`'s. Type alias allows us to
/// declare a `trait` on it.
pub type GenericOptions = Option<Vec<GenericOption>>;
impl GenericOption {
/// Represent `GenericOption` as SQL statement parameter.
fn to_pg_option(&self) -> String {
pub fn to_pg_option(&self) -> String {
if let Some(val) = &self.value {
match self.vartype.as_ref() {
"string" => format!("{} {}", self.name, escape_literal(val)),
"string" => format!("{} '{}'", self.name, val),
_ => format!("{} {}", self.name, val),
}
} else {
@@ -57,11 +61,18 @@ impl GenericOptionExt for GenericOption {
}
/// Represent `GenericOption` as configuration option.
fn to_pg_setting(&self) -> String {
pub fn to_pg_setting(&self) -> String {
if let Some(val) = &self.value {
let name = match self.name.as_str() {
"safekeepers" => "neon.safekeepers",
"wal_acceptor_reconnect" => "neon.safekeeper_reconnect_timeout",
"wal_acceptor_connection_timeout" => "neon.safekeeper_connection_timeout",
it => it,
};
match self.vartype.as_ref() {
"string" => format!("{} = {}", self.name, escape_conf_value(val)),
_ => format!("{} = {}", self.name, val),
"string" => format!("{} = '{}'", name, val),
_ => format!("{} = {}", name, val),
}
} else {
self.name.to_owned()
@@ -96,7 +107,6 @@ impl PgOptionsSerialize for GenericOptions {
.map(|op| op.to_pg_setting())
.collect::<Vec<String>>()
.join("\n")
+ "\n" // newline after last setting
} else {
"".to_string()
}
@@ -105,7 +115,6 @@ impl PgOptionsSerialize for GenericOptions {
pub trait GenericOptionsSearch {
fn find(&self, name: &str) -> Option<String>;
fn find_ref(&self, name: &str) -> Option<&GenericOption>;
}
impl GenericOptionsSearch for GenericOptions {
@@ -115,25 +124,16 @@ impl GenericOptionsSearch for GenericOptions {
let op = ops.iter().find(|s| s.name == name)?;
op.value.clone()
}
/// Lookup option by name, returning ref
fn find_ref(&self, name: &str) -> Option<&GenericOption> {
let ops = self.as_ref()?;
ops.iter().find(|s| s.name == name)
}
}
pub trait RoleExt {
fn to_pg_options(&self) -> String;
}
impl RoleExt for Role {
impl Role {
/// Serialize a list of role parameters into a Postgres-acceptable
/// string of arguments.
fn to_pg_options(&self) -> String {
pub fn to_pg_options(&self) -> String {
// XXX: consider putting LOGIN as a default option somewhere higher, e.g. in control-plane.
let mut params: String = self.options.as_pg_options();
params.push_str(" LOGIN");
// For now, we do not use generic `options` for roles. Once used, add
// `self.options.as_pg_options()` somewhere here.
let mut params: String = "LOGIN".to_string();
if let Some(pass) = &self.encrypted_password {
// Some time ago we supported only md5 and treated all encrypted_password as md5.
@@ -154,17 +154,21 @@ impl RoleExt for Role {
}
}
pub trait DatabaseExt {
fn to_pg_options(&self) -> String;
}
impl Database {
pub fn new(name: PgIdent, owner: PgIdent) -> Self {
Self {
name,
owner,
options: None,
}
}
impl DatabaseExt for Database {
/// Serialize a list of database parameters into a Postgres-acceptable
/// string of arguments.
/// NB: `TEMPLATE` is actually also an identifier, but so far we only need
/// to use `template0` and `template1`, so it is not a problem. Yet in the future
/// it may require a proper quoting too.
fn to_pg_options(&self) -> String {
pub fn to_pg_options(&self) -> String {
let mut params: String = self.options.as_pg_options();
write!(params, " OWNER {}", &self.owner.pg_quote())
.expect("String is documented to not to error during write operations");
@@ -173,6 +177,10 @@ impl DatabaseExt for Database {
}
}
/// String type alias representing Postgres identifier and
/// intended to be used for DB / role names.
pub type PgIdent = String;
/// Generic trait used to provide quoting / encoding for strings used in the
/// Postgres SQL queries and DATABASE_URL.
pub trait Escaping {
@@ -213,11 +221,7 @@ pub fn get_existing_dbs(client: &mut Client) -> Result<Vec<Database>> {
&[],
)?
.iter()
.map(|row| Database {
name: row.get("datname"),
owner: row.get("owner"),
options: None,
})
.map(|row| Database::new(row.get("datname"), row.get("owner")))
.collect();
Ok(postgres_dbs)
@@ -226,7 +230,7 @@ pub fn get_existing_dbs(client: &mut Client) -> Result<Vec<Database>> {
/// Wait for Postgres to become ready to accept connections. It's ready to
/// accept connections when the state-field in `pgdata/postmaster.pid` says
/// 'ready'.
#[instrument(skip_all, fields(pgdata = %pgdata.display()))]
#[instrument(skip(pg))]
pub fn wait_for_postgres(pg: &mut Child, pgdata: &Path) -> Result<()> {
let pid_path = pgdata.join("postmaster.pid");

View File

@@ -1,121 +1,52 @@
use std::fs::File;
use std::path::Path;
use std::str::FromStr;
use anyhow::{anyhow, bail, Result};
use anyhow::Result;
use postgres::config::Config;
use postgres::{Client, NoTls};
use reqwest::StatusCode;
use tracing::{error, info, info_span, instrument, span_enabled, warn, Level};
use serde::Deserialize;
use tracing::{info, info_span, instrument, span_enabled, warn, Level};
use crate::compute::ComputeNode;
use crate::config;
use crate::params::PG_HBA_ALL_MD5;
use crate::pg_helpers::*;
use compute_api::responses::{ControlPlaneComputeStatus, ControlPlaneSpecResponse};
use compute_api::spec::{ComputeSpec, Database, PgIdent, Role};
// Do control plane request and return response if any. In case of error it
// returns a bool flag indicating whether it makes sense to retry the request
// and a string with error message.
fn do_control_plane_request(
uri: &str,
jwt: &str,
) -> Result<ControlPlaneSpecResponse, (bool, String)> {
let resp = reqwest::blocking::Client::new()
.get(uri)
.header("Authorization", jwt)
.send()
.map_err(|e| {
(
true,
format!("could not perform spec request to control plane: {}", e),
)
})?;
match resp.status() {
StatusCode::OK => match resp.json::<ControlPlaneSpecResponse>() {
Ok(spec_resp) => Ok(spec_resp),
Err(e) => Err((
true,
format!("could not deserialize control plane response: {}", e),
)),
},
StatusCode::SERVICE_UNAVAILABLE => {
Err((true, "control plane is temporarily unavailable".to_string()))
}
StatusCode::BAD_GATEWAY => {
// We have a problem with intermittent 502 errors now
// https://github.com/neondatabase/cloud/issues/2353
// It's fine to retry GET request in this case.
Err((true, "control plane request failed with 502".to_string()))
}
// Another code, likely 500 or 404, means that compute is unknown to the control plane
// or some internal failure happened. Doesn't make much sense to retry in this case.
_ => Err((
false,
format!(
"unexpected control plane response status code: {}",
resp.status()
),
)),
}
/// Cluster spec or configuration represented as an optional number of
/// delta operations + final cluster state description.
#[derive(Clone, Deserialize)]
pub struct ComputeSpec {
pub format_version: f32,
pub timestamp: String,
pub operation_uuid: Option<String>,
/// Expected cluster state at the end of transition process.
pub cluster: Cluster,
pub delta_operations: Option<Vec<DeltaOp>>,
}
/// Request spec from the control-plane by compute_id. If `NEON_CONTROL_PLANE_TOKEN`
/// env variable is set, it will be used for authorization.
pub fn get_spec_from_control_plane(
base_uri: &str,
compute_id: &str,
) -> Result<Option<ComputeSpec>> {
let cp_uri = format!("{base_uri}/management/api/v2/computes/{compute_id}/spec");
let jwt: String = match std::env::var("NEON_CONTROL_PLANE_TOKEN") {
Ok(v) => v,
Err(_) => "".to_string(),
};
let mut attempt = 1;
let mut spec: Result<Option<ComputeSpec>> = Ok(None);
/// Cluster state seen from the perspective of the external tools
/// like Rails web console.
#[derive(Clone, Deserialize)]
pub struct Cluster {
pub cluster_id: String,
pub name: String,
pub state: Option<String>,
pub roles: Vec<Role>,
pub databases: Vec<Database>,
pub settings: GenericOptions,
}
info!("getting spec from control plane: {}", cp_uri);
// Do 3 attempts to get spec from the control plane using the following logic:
// - network error -> then retry
// - compute id is unknown or any other error -> bail out
// - no spec for compute yet (Empty state) -> return Ok(None)
// - got spec -> return Ok(Some(spec))
while attempt < 4 {
spec = match do_control_plane_request(&cp_uri, &jwt) {
Ok(spec_resp) => match spec_resp.status {
ControlPlaneComputeStatus::Empty => Ok(None),
ControlPlaneComputeStatus::Attached => {
if let Some(spec) = spec_resp.spec {
Ok(Some(spec))
} else {
bail!("compute is attached, but spec is empty")
}
}
},
Err((retry, msg)) => {
if retry {
Err(anyhow!(msg))
} else {
bail!(msg);
}
}
};
if let Err(e) = &spec {
error!("attempt {} to get spec failed with: {}", attempt, e);
} else {
return spec;
}
attempt += 1;
std::thread::sleep(std::time::Duration::from_millis(100));
}
// All attempts failed, return error.
spec
/// Single cluster state changing operation that could not be represented as
/// a static `Cluster` structure. For example:
/// - DROP DATABASE
/// - DROP ROLE
/// - ALTER ROLE name RENAME TO new_name
/// - ALTER DATABASE name RENAME TO new_name
#[derive(Clone, Deserialize)]
pub struct DeltaOp {
pub action: String,
pub name: PgIdent,
pub new_name: Option<PgIdent>,
}
/// It takes cluster specification and does the following:
@@ -124,7 +55,7 @@ pub fn get_spec_from_control_plane(
pub fn handle_configuration(spec: &ComputeSpec, pgdata_path: &Path) -> Result<()> {
// File `postgresql.conf` is no longer included into `basebackup`, so just
// always write all config into it creating new file.
config::write_postgres_conf(&pgdata_path.join("postgresql.conf"), spec, None)?;
config::write_postgres_conf(&pgdata_path.join("postgresql.conf"), spec)?;
update_pg_hba(pgdata_path)?;
@@ -146,21 +77,6 @@ pub fn update_pg_hba(pgdata_path: &Path) -> Result<()> {
Ok(())
}
/// Create a standby.signal file
pub fn add_standby_signal(pgdata_path: &Path) -> Result<()> {
// XXX: consider making it a part of spec.json
info!("adding standby.signal");
let signalfile = pgdata_path.join("standby.signal");
if !signalfile.exists() {
info!("created standby.signal");
File::create(signalfile)?;
} else {
info!("reused pre-existing standby.signal");
}
Ok(())
}
/// Given a cluster spec json and open transaction it handles roles creation,
/// deletion and update.
#[instrument(skip_all)]
@@ -269,13 +185,17 @@ pub fn handle_roles(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
xact.execute(query.as_str(), &[])?;
}
RoleAction::Create => {
let mut query: String = format!(
"CREATE ROLE {} CREATEROLE CREATEDB BYPASSRLS IN ROLE neon_superuser",
name.pg_quote()
);
let mut query: String = format!("CREATE ROLE {} ", name.pg_quote());
info!("role create query: '{}'", &query);
query.push_str(&role.to_pg_options());
xact.execute(query.as_str(), &[])?;
let grant_query = format!(
"GRANT pg_read_all_data, pg_write_all_data TO {}",
name.pg_quote()
);
xact.execute(grant_query.as_str(), &[])?;
info!("role grant query: '{}'", &grant_query);
}
}
@@ -301,8 +221,8 @@ pub fn handle_roles(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
/// Reassign all dependent objects and delete requested roles.
#[instrument(skip_all)]
pub fn handle_role_deletions(spec: &ComputeSpec, connstr: &str, client: &mut Client) -> Result<()> {
if let Some(ops) = &spec.delta_operations {
pub fn handle_role_deletions(node: &ComputeNode, client: &mut Client) -> Result<()> {
if let Some(ops) = &node.spec.delta_operations {
// First, reassign all dependent objects to db owners.
info!("reassigning dependent objects of to-be-deleted roles");
@@ -319,7 +239,7 @@ pub fn handle_role_deletions(spec: &ComputeSpec, connstr: &str, client: &mut Cli
// Check that role is still present in Postgres, as this could be a
// restart with the same spec after role deletion.
if op.action == "delete_role" && existing_roles.iter().any(|r| r.name == op.name) {
reassign_owned_objects(spec, connstr, &op.name)?;
reassign_owned_objects(node, &op.name)?;
}
}
@@ -343,10 +263,10 @@ pub fn handle_role_deletions(spec: &ComputeSpec, connstr: &str, client: &mut Cli
}
// Reassign all owned objects in all databases to the owner of the database.
fn reassign_owned_objects(spec: &ComputeSpec, connstr: &str, role_name: &PgIdent) -> Result<()> {
for db in &spec.cluster.databases {
fn reassign_owned_objects(node: &ComputeNode, role_name: &PgIdent) -> Result<()> {
for db in &node.spec.cluster.databases {
if db.owner != *role_name {
let mut conf = Config::from_str(connstr)?;
let mut conf = Config::from_str(node.connstr.as_str())?;
conf.dbname(&db.name);
let mut client = conf.connect(NoTls)?;
@@ -397,44 +317,10 @@ pub fn handle_databases(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
// We do not check either DB exists or not,
// Postgres will take care of it for us
"delete_db" => {
// In Postgres we can't drop a database if it is a template.
// So we need to unset the template flag first, but it could
// be a retry, so we could've already dropped the database.
// Check that database exists first to make it idempotent.
let unset_template_query: String = format!(
"
DO $$
BEGIN
IF EXISTS(
SELECT 1
FROM pg_catalog.pg_database
WHERE datname = {}
)
THEN
ALTER DATABASE {} is_template false;
END IF;
END
$$;",
escape_literal(&op.name),
&op.name.pg_quote()
);
// Use FORCE to drop database even if there are active connections.
// We run this from `cloud_admin`, so it should have enough privileges.
// NB: there could be other db states, which prevent us from dropping
// the database. For example, if db is used by any active subscription
// or replication slot.
// TODO: deal with it once we allow logical replication. Proper fix should
// involve returning an error code to the control plane, so it could
// figure out that this is a non-retryable error, return it to the user
// and fail operation permanently.
let drop_db_query: String = format!(
"DROP DATABASE IF EXISTS {} WITH (FORCE)",
&op.name.pg_quote()
);
let query: String = format!("DROP DATABASE IF EXISTS {}", &op.name.pg_quote());
warn!("deleting database '{}'", &op.name);
client.execute(unset_template_query.as_str(), &[])?;
client.execute(drop_db_query.as_str(), &[])?;
client.execute(query.as_str(), &[])?;
}
"rename_db" => {
let new_name = op.new_name.as_ref().unwrap();
@@ -498,19 +384,14 @@ pub fn handle_databases(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
name.pg_quote(),
db.owner.pg_quote()
);
let _guard = info_span!("executing", query).entered();
let _ = info_span!("executing", query).entered();
client.execute(query.as_str(), &[])?;
}
DatabaseAction::Create => {
let mut query: String = format!("CREATE DATABASE {} ", name.pg_quote());
query.push_str(&db.to_pg_options());
let _guard = info_span!("executing", query).entered();
let _ = info_span!("executing", query).entered();
client.execute(query.as_str(), &[])?;
let grant_query: String = format!(
"GRANT ALL PRIVILEGES ON DATABASE {} TO neon_superuser",
name.pg_quote()
);
client.execute(grant_query.as_str(), &[])?;
}
};
@@ -530,14 +411,42 @@ pub fn handle_databases(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
/// Grant CREATE ON DATABASE to the database owner and do some other alters and grants
/// to allow users creating trusted extensions and re-creating `public` schema, for example.
#[instrument(skip_all)]
pub fn handle_grants(spec: &ComputeSpec, connstr: &str) -> Result<()> {
pub fn handle_grants(node: &ComputeNode, client: &mut Client) -> Result<()> {
let spec = &node.spec;
info!("cluster spec grants:");
// We now have a separate `web_access` role to connect to the database
// via the web interface and proxy link auth. And also we grant a
// read / write all data privilege to every role. So also grant
// create to everyone.
// XXX: later we should stop messing with Postgres ACL in such horrible
// ways.
let roles = spec
.cluster
.roles
.iter()
.map(|r| r.name.pg_quote())
.collect::<Vec<_>>();
for db in &spec.cluster.databases {
let dbname = &db.name;
let query: String = format!(
"GRANT CREATE ON DATABASE {} TO {}",
dbname.pg_quote(),
roles.join(", ")
);
info!("grant query {}", &query);
client.execute(query.as_str(), &[])?;
}
// Do some per-database access adjustments. We'd better do this at db creation time,
// but CREATE DATABASE isn't transactional. So we cannot create db + do some grants
// atomically.
for db in &spec.cluster.databases {
let mut conf = Config::from_str(connstr)?;
for db in &node.spec.cluster.databases {
let mut conf = Config::from_str(node.connstr.as_str())?;
conf.dbname(&db.name);
let mut db_client = conf.connect(NoTls)?;
@@ -603,18 +512,3 @@ pub fn handle_grants(spec: &ComputeSpec, connstr: &str) -> Result<()> {
Ok(())
}
/// Create required system extensions
#[instrument(skip_all)]
pub fn handle_extensions(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
if let Some(libs) = spec.cluster.settings.find("shared_preload_libraries") {
if libs.contains("pg_stat_statements") {
// Create extension only if this compute really needs it
let query = "CREATE EXTENSION IF NOT EXISTS pg_stat_statements";
info!("creating system extensions with query: {}", query);
client.simple_query(query)?;
}
}
Ok(())
}

View File

@@ -1,98 +0,0 @@
// Utils for running sync_safekeepers
use anyhow::Result;
use tracing::info;
use utils::lsn::Lsn;
#[derive(Copy, Clone, Debug)]
pub enum TimelineStatusResponse {
NotFound,
Ok(TimelineStatusOkResponse),
}
#[derive(Copy, Clone, Debug)]
pub struct TimelineStatusOkResponse {
flush_lsn: Lsn,
commit_lsn: Lsn,
}
/// Get a safekeeper's metadata for our timeline. The id is only used for logging
pub async fn ping_safekeeper(
id: String,
config: tokio_postgres::Config,
) -> Result<TimelineStatusResponse> {
// TODO add retries
// Connect
info!("connecting to {}", id);
let (client, conn) = config.connect(tokio_postgres::NoTls).await?;
tokio::spawn(async move {
if let Err(e) = conn.await {
eprintln!("connection error: {}", e);
}
});
// Query
info!("querying {}", id);
let result = client.simple_query("TIMELINE_STATUS").await?;
// Parse result
info!("done with {}", id);
if let postgres::SimpleQueryMessage::Row(row) = &result[0] {
use std::str::FromStr;
let response = TimelineStatusResponse::Ok(TimelineStatusOkResponse {
flush_lsn: Lsn::from_str(row.get("flush_lsn").unwrap())?,
commit_lsn: Lsn::from_str(row.get("commit_lsn").unwrap())?,
});
Ok(response)
} else {
// Timeline doesn't exist
Ok(TimelineStatusResponse::NotFound)
}
}
/// Given a quorum of responses, check if safekeepers are synced at some Lsn
pub fn check_if_synced(responses: Vec<TimelineStatusResponse>) -> Option<Lsn> {
// Check if all responses are ok
let ok_responses: Vec<TimelineStatusOkResponse> = responses
.iter()
.filter_map(|r| match r {
TimelineStatusResponse::Ok(ok_response) => Some(ok_response),
_ => None,
})
.cloned()
.collect();
if ok_responses.len() < responses.len() {
info!(
"not synced. Only {} out of {} know about this timeline",
ok_responses.len(),
responses.len()
);
return None;
}
// Get the min and the max of everything
let commit: Vec<Lsn> = ok_responses.iter().map(|r| r.commit_lsn).collect();
let flush: Vec<Lsn> = ok_responses.iter().map(|r| r.flush_lsn).collect();
let commit_max = commit.iter().max().unwrap();
let commit_min = commit.iter().min().unwrap();
let flush_max = flush.iter().max().unwrap();
let flush_min = flush.iter().min().unwrap();
// Check that all values are equal
if commit_min != commit_max {
info!("not synced. {:?} {:?}", commit_min, commit_max);
return None;
}
if flush_min != flush_max {
info!("not synced. {:?} {:?}", flush_min, flush_max);
return None;
}
// Check that commit == flush
if commit_max != flush_max {
info!("not synced. {:?} {:?}", commit_max, flush_max);
return None;
}
Some(*commit_max)
}

View File

@@ -178,11 +178,6 @@
"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"
}
]
},
@@ -205,43 +200,5 @@
"name": "zenith new",
"new_name": "zenith \"new\""
}
],
"remote_extensions": {
"library_index": {
"anon": "anon",
"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": {
"anon": {
"archive_path": "5834329303/v15/extensions/anon.tar.zst",
"control_data": {
"anon.control": "# PostgreSQL Anonymizer (anon) extension\ncomment = ''Data anonymization tools''\ndefault_version = ''1.1.0''\ndirectory=''extension/anon''\nrelocatable = false\nrequires = ''pgcrypto''\nsuperuser = false\nmodule_pathname = ''$libdir/anon''\ntrusted = true\n"
}
},
"postgis": {
"archive_path": "5834329303/v15/extensions/postgis.tar.zst",
"control_data": {
"postgis.control": "# postgis extension\ncomment = ''PostGIS geometry and geography spatial types and functions''\ndefault_version = ''3.3.2''\nmodule_pathname = ''$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": [
"anon"
],
"public_extensions": [
"postgis"
]
}
]
}

View File

@@ -1,13 +1,14 @@
#[cfg(test)]
mod pg_helpers_tests {
use std::fs::File;
use compute_api::spec::{ComputeSpec, GenericOption, GenericOptions, PgIdent};
use compute_tools::pg_helpers::*;
use compute_tools::spec::ComputeSpec;
#[test]
fn params_serialize() {
let file = File::open("../libs/compute_api/tests/cluster_spec.json").unwrap();
let file = File::open("tests/cluster_spec.json").unwrap();
let spec: ComputeSpec = serde_json::from_reader(file).unwrap();
assert_eq!(
@@ -16,41 +17,18 @@ mod pg_helpers_tests {
);
assert_eq!(
spec.cluster.roles.first().unwrap().to_pg_options(),
" LOGIN PASSWORD 'md56b1d16b78004bbd51fa06af9eda75972'"
"LOGIN PASSWORD 'md56b1d16b78004bbd51fa06af9eda75972'"
);
}
#[test]
fn settings_serialize() {
let file = File::open("../libs/compute_api/tests/cluster_spec.json").unwrap();
let file = File::open("tests/cluster_spec.json").unwrap();
let spec: ComputeSpec = serde_json::from_reader(file).unwrap();
assert_eq!(
spec.cluster.settings.as_pg_settings(),
r#"fsync = off
wal_level = replica
hot_standby = on
neon.safekeepers = '127.0.0.1:6502,127.0.0.1:6503,127.0.0.1:6501'
wal_log_hints = on
log_connections = on
shared_buffers = 32768
port = 55432
max_connections = 100
max_wal_senders = 10
listen_addresses = '0.0.0.0'
wal_sender_timeout = 0
password_encryption = md5
maintenance_work_mem = 65536
max_parallel_workers = 8
max_worker_processes = 8
neon.tenant_id = 'b0554b632bd4d547a63b86c3630317e8'
max_replication_slots = 10
neon.timeline_id = '2414a61ffc94e428f14b5758fe308e13'
shared_preload_libraries = 'neon'
synchronous_standby_names = 'walproposer'
neon.pageserver_connstring = 'host=127.0.0.1 port=6400'
test.escaping = 'here''s a backslash \\ and a quote '' and a double-quote " hooray'
"#
"fsync = off\nwal_level = replica\nhot_standby = on\nneon.safekeepers = '127.0.0.1:6502,127.0.0.1:6503,127.0.0.1:6501'\nwal_log_hints = on\nlog_connections = on\nshared_buffers = 32768\nport = 55432\nmax_connections = 100\nmax_wal_senders = 10\nlisten_addresses = '0.0.0.0'\nwal_sender_timeout = 0\npassword_encryption = md5\nmaintenance_work_mem = 65536\nmax_parallel_workers = 8\nmax_worker_processes = 8\nneon.tenant_id = 'b0554b632bd4d547a63b86c3630317e8'\nmax_replication_slots = 10\nneon.timeline_id = '2414a61ffc94e428f14b5758fe308e13'\nshared_preload_libraries = 'neon'\nsynchronous_standby_names = 'walproposer'\nneon.pageserver_connstring = 'host=127.0.0.1 port=6400'"
);
}
@@ -89,12 +67,4 @@ test.escaping = 'here''s a backslash \\ and a quote '' and a double-quote " hoor
assert_eq!(none_generic_options.find("missed_value"), None);
assert_eq!(none_generic_options.find("invalid_value"), None);
}
#[test]
fn test_escape_literal() {
assert_eq!(escape_literal("test"), "'test'");
assert_eq!(escape_literal("test'"), "'test'''");
assert_eq!(escape_literal("test\\'"), "E'test\\\\'''");
assert_eq!(escape_literal("test\\'\\'"), "E'test\\\\''\\\\'''");
}
}

View File

@@ -12,27 +12,20 @@ git-version.workspace = true
nix.workspace = true
once_cell.workspace = true
postgres.workspace = true
hex.workspace = true
hyper.workspace = true
regex.workspace = true
reqwest = { workspace = true, features = ["blocking", "json"] }
serde.workspace = true
serde_json.workspace = true
serde_with.workspace = true
tar.workspace = true
thiserror.workspace = true
toml.workspace = true
tokio.workspace = true
url.workspace = true
# Note: Do not directly depend on pageserver or safekeeper; use pageserver_api or safekeeper_api
# instead, so that recompile times are better.
pageserver_api.workspace = true
postgres_backend.workspace = true
safekeeper_api.workspace = true
postgres_connection.workspace = true
storage_broker.workspace = true
utils.workspace = true
compute_api.workspace = true
workspace_hack.workspace = true
tracing.workspace = true

View File

@@ -2,8 +2,7 @@
[pageserver]
listen_pg_addr = '127.0.0.1:64000'
listen_http_addr = '127.0.0.1:9898'
pg_auth_type = 'Trust'
http_auth_type = 'Trust'
auth_type = 'Trust'
[[safekeepers]]
id = 1

View File

@@ -1,11 +1,9 @@
# Minimal neon environment with one safekeeper. This is equivalent to the built-in
# defaults that you get with no --config
[[pageservers]]
id=1
[pageserver]
listen_pg_addr = '127.0.0.1:64000'
listen_http_addr = '127.0.0.1:9898'
pg_auth_type = 'Trust'
http_auth_type = 'Trust'
auth_type = 'Trust'
[[safekeepers]]
id = 1

View File

@@ -1,105 +0,0 @@
use crate::{background_process, local_env::LocalEnv};
use anyhow::anyhow;
use serde::{Deserialize, Serialize};
use serde_with::{serde_as, DisplayFromStr};
use std::{path::PathBuf, process::Child};
use utils::id::{NodeId, TenantId};
pub struct AttachmentService {
env: LocalEnv,
listen: String,
path: PathBuf,
}
const COMMAND: &str = "attachment_service";
#[serde_as]
#[derive(Serialize, Deserialize)]
pub struct AttachHookRequest {
#[serde_as(as = "DisplayFromStr")]
pub tenant_id: TenantId,
pub pageserver_id: Option<NodeId>,
}
#[derive(Serialize, Deserialize)]
pub struct AttachHookResponse {
pub gen: Option<u32>,
}
impl AttachmentService {
pub fn from_env(env: &LocalEnv) -> Self {
let path = env.base_data_dir.join("attachments.json");
// Makes no sense to construct this if pageservers aren't going to use it: assume
// pageservers have control plane API set
let listen_url = env.control_plane_api.clone().unwrap();
let listen = format!(
"{}:{}",
listen_url.host_str().unwrap(),
listen_url.port().unwrap()
);
Self {
env: env.clone(),
path,
listen,
}
}
fn pid_file(&self) -> PathBuf {
self.env.base_data_dir.join("attachment_service.pid")
}
pub fn start(&self) -> anyhow::Result<Child> {
let path_str = self.path.to_string_lossy();
background_process::start_process(
COMMAND,
&self.env.base_data_dir,
&self.env.attachment_service_bin(),
["-l", &self.listen, "-p", &path_str],
[],
background_process::InitialPidFile::Create(&self.pid_file()),
// TODO: a real status check
|| Ok(true),
)
}
pub fn stop(&self, immediate: bool) -> anyhow::Result<()> {
background_process::stop_process(immediate, COMMAND, &self.pid_file())
}
/// Call into the attach_hook API, for use before handing out attachments to pageservers
pub fn attach_hook(
&self,
tenant_id: TenantId,
pageserver_id: NodeId,
) -> anyhow::Result<Option<u32>> {
use hyper::StatusCode;
let url = self
.env
.control_plane_api
.clone()
.unwrap()
.join("attach_hook")
.unwrap();
let client = reqwest::blocking::ClientBuilder::new()
.build()
.expect("Failed to construct http client");
let request = AttachHookRequest {
tenant_id,
pageserver_id: Some(pageserver_id),
};
let response = client.post(url).json(&request).send()?;
if response.status() != StatusCode::OK {
return Err(anyhow!("Unexpected status {}", response.status()));
}
let response = response.json::<AttachHookResponse>()?;
Ok(response.gen)
}
}

View File

@@ -10,7 +10,7 @@
//! (non-Neon binaries don't necessarily follow our pidfile conventions).
//! The pid stored in the file is later used to stop the service.
//!
//! See the [`lock_file`](utils::lock_file) module for more info.
//! See [`lock_file`] module for more info.
use std::ffi::OsStr;
use std::io::Write;
@@ -180,11 +180,6 @@ pub fn stop_process(immediate: bool, process_name: &str, pid_file: &Path) -> any
}
// Wait until process is gone
wait_until_stopped(process_name, pid)?;
Ok(())
}
pub fn wait_until_stopped(process_name: &str, pid: Pid) -> anyhow::Result<()> {
for retries in 0..RETRIES {
match process_has_stopped(pid) {
Ok(true) => {

View File

@@ -1,274 +0,0 @@
/// The attachment service mimics the aspects of the control plane API
/// that are required for a pageserver to operate.
///
/// This enables running & testing pageservers without a full-blown
/// deployment of the Neon cloud platform.
///
use anyhow::anyhow;
use clap::Parser;
use hex::FromHex;
use hyper::StatusCode;
use hyper::{Body, Request, Response};
use serde::{Deserialize, Serialize};
use std::path::{Path, PathBuf};
use std::{collections::HashMap, sync::Arc};
use utils::logging::{self, LogFormat};
use utils::{
http::{
endpoint::{self},
error::ApiError,
json::{json_request, json_response},
RequestExt, RouterBuilder,
},
id::{NodeId, TenantId},
tcp_listener,
};
use pageserver_api::control_api::{
ReAttachRequest, ReAttachResponse, ReAttachResponseTenant, ValidateRequest, ValidateResponse,
ValidateResponseTenant,
};
use control_plane::attachment_service::{AttachHookRequest, AttachHookResponse};
#[derive(Parser)]
#[command(author, version, about, long_about = None)]
#[command(arg_required_else_help(true))]
struct Cli {
/// Host and port to listen on, like `127.0.0.1:1234`
#[arg(short, long)]
listen: std::net::SocketAddr,
/// Path to the .json file to store state (will be created if it doesn't exist)
#[arg(short, long)]
path: PathBuf,
}
// The persistent state of each Tenant
#[derive(Serialize, Deserialize, Clone)]
struct TenantState {
// Currently attached pageserver
pageserver: Option<NodeId>,
// Latest generation number: next time we attach, increment this
// and use the incremented number when attaching
generation: u32,
}
fn to_hex_map<S, V>(input: &HashMap<TenantId, V>, serializer: S) -> Result<S::Ok, S::Error>
where
S: serde::Serializer,
V: Clone + Serialize,
{
let transformed = input.iter().map(|(k, v)| (hex::encode(k), v.clone()));
transformed
.collect::<HashMap<String, V>>()
.serialize(serializer)
}
fn from_hex_map<'de, D, V>(deserializer: D) -> Result<HashMap<TenantId, V>, D::Error>
where
D: serde::de::Deserializer<'de>,
V: Deserialize<'de>,
{
let hex_map = HashMap::<String, V>::deserialize(deserializer)?;
hex_map
.into_iter()
.map(|(k, v)| {
TenantId::from_hex(k)
.map(|k| (k, v))
.map_err(serde::de::Error::custom)
})
.collect()
}
// Top level state available to all HTTP handlers
#[derive(Serialize, Deserialize)]
struct PersistentState {
#[serde(serialize_with = "to_hex_map", deserialize_with = "from_hex_map")]
tenants: HashMap<TenantId, TenantState>,
#[serde(skip)]
path: PathBuf,
}
impl PersistentState {
async fn save(&self) -> anyhow::Result<()> {
let bytes = serde_json::to_vec(self)?;
tokio::fs::write(&self.path, &bytes).await?;
Ok(())
}
async fn load(path: &Path) -> anyhow::Result<Self> {
let bytes = tokio::fs::read(path).await?;
let mut decoded = serde_json::from_slice::<Self>(&bytes)?;
decoded.path = path.to_owned();
Ok(decoded)
}
async fn load_or_new(path: &Path) -> Self {
match Self::load(path).await {
Ok(s) => {
tracing::info!("Loaded state file at {}", path.display());
s
}
Err(e)
if e.downcast_ref::<std::io::Error>()
.map(|e| e.kind() == std::io::ErrorKind::NotFound)
.unwrap_or(false) =>
{
tracing::info!("Will create state file at {}", path.display());
Self {
tenants: HashMap::new(),
path: path.to_owned(),
}
}
Err(e) => {
panic!("Failed to load state from '{}': {e:#} (maybe your .neon/ dir was written by an older version?)", path.display())
}
}
}
}
/// State available to HTTP request handlers
#[derive(Clone)]
struct State {
inner: Arc<tokio::sync::RwLock<PersistentState>>,
}
impl State {
fn new(persistent_state: PersistentState) -> State {
Self {
inner: Arc::new(tokio::sync::RwLock::new(persistent_state)),
}
}
}
#[inline(always)]
fn get_state(request: &Request<Body>) -> &State {
request
.data::<Arc<State>>()
.expect("unknown state type")
.as_ref()
}
/// Pageserver calls into this on startup, to learn which tenants it should attach
async fn handle_re_attach(mut req: Request<Body>) -> Result<Response<Body>, ApiError> {
let reattach_req = json_request::<ReAttachRequest>(&mut req).await?;
let state = get_state(&req).inner.clone();
let mut locked = state.write().await;
let mut response = ReAttachResponse {
tenants: Vec::new(),
};
for (t, state) in &mut locked.tenants {
if state.pageserver == Some(reattach_req.node_id) {
state.generation += 1;
response.tenants.push(ReAttachResponseTenant {
id: *t,
generation: state.generation,
});
}
}
locked.save().await.map_err(ApiError::InternalServerError)?;
json_response(StatusCode::OK, response)
}
/// Pageserver calls into this before doing deletions, to confirm that it still
/// holds the latest generation for the tenants with deletions enqueued
async fn handle_validate(mut req: Request<Body>) -> Result<Response<Body>, ApiError> {
let validate_req = json_request::<ValidateRequest>(&mut req).await?;
let locked = get_state(&req).inner.read().await;
let mut response = ValidateResponse {
tenants: Vec::new(),
};
for req_tenant in validate_req.tenants {
if let Some(tenant_state) = locked.tenants.get(&req_tenant.id) {
let valid = tenant_state.generation == req_tenant.gen;
response.tenants.push(ValidateResponseTenant {
id: req_tenant.id,
valid,
});
}
}
json_response(StatusCode::OK, response)
}
/// Call into this before attaching a tenant to a pageserver, to acquire a generation number
/// (in the real control plane this is unnecessary, because the same program is managing
/// generation numbers and doing attachments).
async fn handle_attach_hook(mut req: Request<Body>) -> Result<Response<Body>, ApiError> {
let attach_req = json_request::<AttachHookRequest>(&mut req).await?;
let state = get_state(&req).inner.clone();
let mut locked = state.write().await;
let tenant_state = locked
.tenants
.entry(attach_req.tenant_id)
.or_insert_with(|| TenantState {
pageserver: attach_req.pageserver_id,
generation: 0,
});
if attach_req.pageserver_id.is_some() {
tenant_state.generation += 1;
}
tenant_state.pageserver = attach_req.pageserver_id;
let generation = tenant_state.generation;
locked.save().await.map_err(ApiError::InternalServerError)?;
json_response(
StatusCode::OK,
AttachHookResponse {
gen: attach_req.pageserver_id.map(|_| generation),
},
)
}
fn make_router(persistent_state: PersistentState) -> RouterBuilder<hyper::Body, ApiError> {
endpoint::make_router()
.data(Arc::new(State::new(persistent_state)))
.post("/re-attach", handle_re_attach)
.post("/validate", handle_validate)
.post("/attach_hook", handle_attach_hook)
}
#[tokio::main]
async fn main() -> anyhow::Result<()> {
logging::init(
LogFormat::Plain,
logging::TracingErrorLayerEnablement::Disabled,
)?;
let args = Cli::parse();
tracing::info!(
"Starting, state at {}, listening on {}",
args.path.to_string_lossy(),
args.listen
);
let persistent_state = PersistentState::load_or_new(&args.path).await;
let http_listener = tcp_listener::bind(args.listen)?;
let router = make_router(persistent_state)
.build()
.map_err(|err| anyhow!(err))?;
let service = utils::http::RouterService::new(router).unwrap();
let server = hyper::Server::from_tcp(http_listener)?.serve(service);
tracing::info!("Serving on {0}", args.listen);
server.await?;
Ok(())
}

View File

@@ -7,9 +7,7 @@
//!
use anyhow::{anyhow, bail, Context, Result};
use clap::{value_parser, Arg, ArgAction, ArgMatches, Command};
use compute_api::spec::ComputeMode;
use control_plane::attachment_service::AttachmentService;
use control_plane::endpoint::ComputeControlPlane;
use control_plane::compute::ComputeControlPlane;
use control_plane::local_env::LocalEnv;
use control_plane::pageserver::PageServerNode;
use control_plane::safekeeper::SafekeeperNode;
@@ -19,7 +17,6 @@ use pageserver_api::{
DEFAULT_HTTP_LISTEN_ADDR as DEFAULT_PAGESERVER_HTTP_ADDR,
DEFAULT_PG_LISTEN_ADDR as DEFAULT_PAGESERVER_PG_ADDR,
};
use postgres_backend::AuthType;
use safekeeper_api::{
DEFAULT_HTTP_LISTEN_PORT as DEFAULT_SAFEKEEPER_HTTP_PORT,
DEFAULT_PG_LISTEN_PORT as DEFAULT_SAFEKEEPER_PG_PORT,
@@ -33,6 +30,7 @@ use utils::{
auth::{Claims, Scope},
id::{NodeId, TenantId, TenantTimelineId, TimelineId},
lsn::Lsn,
postgres_backend::AuthType,
project_git_version,
};
@@ -42,33 +40,27 @@ const DEFAULT_PAGESERVER_ID: NodeId = NodeId(1);
const DEFAULT_BRANCH_NAME: &str = "main";
project_git_version!(GIT_VERSION);
const DEFAULT_PG_VERSION: &str = "15";
const DEFAULT_PAGESERVER_CONTROL_PLANE_API: &str = "http://127.0.0.1:1234/";
const DEFAULT_PG_VERSION: &str = "14";
fn default_conf() -> String {
format!(
r#"
# Default built-in configuration, defined in main.rs
control_plane_api = '{DEFAULT_PAGESERVER_CONTROL_PLANE_API}'
[broker]
listen_addr = '{DEFAULT_BROKER_ADDR}'
[[pageservers]]
[pageserver]
id = {DEFAULT_PAGESERVER_ID}
listen_pg_addr = '{DEFAULT_PAGESERVER_PG_ADDR}'
listen_http_addr = '{DEFAULT_PAGESERVER_HTTP_ADDR}'
pg_auth_type = '{trust_auth}'
http_auth_type = '{trust_auth}'
auth_type = '{pageserver_auth_type}'
[[safekeepers]]
id = {DEFAULT_SAFEKEEPER_ID}
pg_port = {DEFAULT_SAFEKEEPER_PG_PORT}
http_port = {DEFAULT_SAFEKEEPER_HTTP_PORT}
"#,
trust_auth = AuthType::Trust,
pageserver_auth_type = AuthType::Trust,
)
}
@@ -113,10 +105,8 @@ fn main() -> Result<()> {
"start" => handle_start_all(sub_args, &env),
"stop" => handle_stop_all(sub_args, &env),
"pageserver" => handle_pageserver(sub_args, &env),
"attachment_service" => handle_attachment_service(sub_args, &env),
"pg" => handle_pg(sub_args, &env),
"safekeeper" => handle_safekeeper(sub_args, &env),
"endpoint" => handle_endpoint(sub_args, &env),
"pg" => bail!("'pg' subcommand has been renamed to 'endpoint'"),
_ => bail!("unexpected subcommand {sub_name}"),
};
@@ -259,7 +249,7 @@ fn get_timeline_infos(
env: &local_env::LocalEnv,
tenant_id: &TenantId,
) -> Result<HashMap<TimelineId, TimelineInfo>> {
Ok(get_default_pageserver(env)
Ok(PageServerNode::from_env(env)
.timeline_list(tenant_id)?
.into_iter()
.map(|timeline_info| (timeline_info.timeline_id, timeline_info))
@@ -315,35 +305,21 @@ fn handle_init(init_match: &ArgMatches) -> anyhow::Result<LocalEnv> {
let mut env =
LocalEnv::parse_config(&toml_file).context("Failed to create neon configuration")?;
let force = init_match.get_flag("force");
env.init(pg_version, force)
env.init(pg_version)
.context("Failed to initialize neon repository")?;
// Initialize pageserver, create initial tenant and timeline.
for ps_conf in &env.pageservers {
PageServerNode::from_env(&env, ps_conf)
.initialize(&pageserver_config_overrides(init_match))
.unwrap_or_else(|e| {
eprintln!("pageserver init failed: {e:?}");
exit(1);
});
}
let pageserver = PageServerNode::from_env(&env);
pageserver
.initialize(&pageserver_config_overrides(init_match))
.unwrap_or_else(|e| {
eprintln!("pageserver init failed: {e:?}");
exit(1);
});
Ok(env)
}
/// The default pageserver is the one where CLI tenant/timeline operations are sent by default.
/// For typical interactive use, one would just run with a single pageserver. Scenarios with
/// tenant/timeline placement across multiple pageservers are managed by python test code rather
/// than this CLI.
fn get_default_pageserver(env: &local_env::LocalEnv) -> PageServerNode {
let ps_conf = env
.pageservers
.first()
.expect("Config is validated to contain at least one pageserver");
PageServerNode::from_env(env, ps_conf)
}
fn pageserver_config_overrides(init_match: &ArgMatches) -> Vec<&str> {
init_match
.get_many::<String>("pageserver-config-override")
@@ -354,7 +330,7 @@ fn pageserver_config_overrides(init_match: &ArgMatches) -> Vec<&str> {
}
fn handle_tenant(tenant_match: &ArgMatches, env: &mut local_env::LocalEnv) -> anyhow::Result<()> {
let pageserver = get_default_pageserver(env);
let pageserver = PageServerNode::from_env(env);
match tenant_match.subcommand() {
Some(("list", _)) => {
for t in pageserver.tenant_list()? {
@@ -362,25 +338,13 @@ fn handle_tenant(tenant_match: &ArgMatches, env: &mut local_env::LocalEnv) -> an
}
}
Some(("create", create_match)) => {
let initial_tenant_id = parse_tenant_id(create_match)?;
let tenant_conf: HashMap<_, _> = create_match
.get_many::<String>("config")
.map(|vals| vals.flat_map(|c| c.split_once(':')).collect())
.unwrap_or_default();
// If tenant ID was not specified, generate one
let tenant_id = parse_tenant_id(create_match)?.unwrap_or_else(TenantId::generate);
let generation = if env.control_plane_api.is_some() {
// We must register the tenant with the attachment service, so
// that when the pageserver restarts, it will be re-attached.
let attachment_service = AttachmentService::from_env(env);
attachment_service.attach_hook(tenant_id, pageserver.conf.id)?
} else {
None
};
pageserver.tenant_create(tenant_id, generation, tenant_conf)?;
println!("tenant {tenant_id} successfully created on the pageserver");
let new_tenant_id = pageserver.tenant_create(initial_tenant_id, tenant_conf)?;
println!("tenant {new_tenant_id} successfully created on the pageserver");
// Create an initial timeline for the new tenant
let new_timeline_id = parse_timeline_id(create_match)?;
@@ -390,7 +354,7 @@ fn handle_tenant(tenant_match: &ArgMatches, env: &mut local_env::LocalEnv) -> an
.context("Failed to parse postgres version from the argument string")?;
let timeline_info = pageserver.timeline_create(
tenant_id,
new_tenant_id,
new_timeline_id,
None,
None,
@@ -401,17 +365,17 @@ fn handle_tenant(tenant_match: &ArgMatches, env: &mut local_env::LocalEnv) -> an
env.register_branch_mapping(
DEFAULT_BRANCH_NAME.to_string(),
tenant_id,
new_tenant_id,
new_timeline_id,
)?;
println!(
"Created an initial timeline '{new_timeline_id}' at Lsn {last_record_lsn} for tenant: {tenant_id}",
"Created an initial timeline '{new_timeline_id}' at Lsn {last_record_lsn} for tenant: {new_tenant_id}",
);
if create_match.get_flag("set-default") {
println!("Setting tenant {tenant_id} as a default one");
env.default_tenant_id = Some(tenant_id);
println!("Setting tenant {new_tenant_id} as a default one");
env.default_tenant_id = Some(new_tenant_id);
}
}
Some(("set-default", set_default_match)) => {
@@ -439,7 +403,7 @@ fn handle_tenant(tenant_match: &ArgMatches, env: &mut local_env::LocalEnv) -> an
}
fn handle_timeline(timeline_match: &ArgMatches, env: &mut local_env::LocalEnv) -> Result<()> {
let pageserver = get_default_pageserver(env);
let pageserver = PageServerNode::from_env(env);
match timeline_match.subcommand() {
Some(("list", list_match)) => {
@@ -505,19 +469,10 @@ fn handle_timeline(timeline_match: &ArgMatches, env: &mut local_env::LocalEnv) -
let mut cplane = ComputeControlPlane::load(env.clone())?;
println!("Importing timeline into pageserver ...");
pageserver.timeline_import(tenant_id, timeline_id, base, pg_wal, pg_version)?;
println!("Creating node for imported timeline ...");
env.register_branch_mapping(name.to_string(), tenant_id, timeline_id)?;
println!("Creating endpoint for imported timeline ...");
cplane.new_endpoint(
name,
tenant_id,
timeline_id,
None,
None,
pg_version,
ComputeMode::Primary,
DEFAULT_PAGESERVER_ID,
)?;
cplane.new_node(tenant_id, name, timeline_id, None, None, pg_version)?;
println!("Done");
}
Some(("branch", branch_match)) => {
@@ -565,11 +520,12 @@ fn handle_timeline(timeline_match: &ArgMatches, env: &mut local_env::LocalEnv) -
Ok(())
}
fn handle_endpoint(ep_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<()> {
let (sub_name, sub_args) = match ep_match.subcommand() {
Some(ep_subcommand_data) => ep_subcommand_data,
None => bail!("no endpoint subcommand provided"),
fn handle_pg(pg_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<()> {
let (sub_name, sub_args) = match pg_match.subcommand() {
Some(pg_subcommand_data) => pg_subcommand_data,
None => bail!("no pg subcommand provided"),
};
let mut cplane = ComputeControlPlane::load(env.clone())?;
// All subcommands take an optional --tenant-id option
@@ -589,7 +545,7 @@ fn handle_endpoint(ep_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<(
table.load_preset(comfy_table::presets::NOTHING);
table.set_header([
"ENDPOINT",
"NODE",
"ADDRESS",
"TIMELINE",
"BRANCH NAME",
@@ -597,39 +553,39 @@ fn handle_endpoint(ep_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<(
"STATUS",
]);
for (endpoint_id, endpoint) in cplane
.endpoints
for ((_, node_name), node) in cplane
.nodes
.iter()
.filter(|(_, endpoint)| endpoint.tenant_id == tenant_id)
.filter(|((node_tenant_id, _), _)| node_tenant_id == &tenant_id)
{
let lsn_str = match endpoint.mode {
ComputeMode::Static(lsn) => {
// -> read-only endpoint
// Use the node's LSN.
lsn.to_string()
}
_ => {
// -> primary endpoint or hot replica
let lsn_str = match node.lsn {
None => {
// -> primary node
// Use the LSN at the end of the timeline.
timeline_infos
.get(&endpoint.timeline_id)
.get(&node.timeline_id)
.map(|bi| bi.last_record_lsn.to_string())
.unwrap_or_else(|| "?".to_string())
}
Some(lsn) => {
// -> read-only node
// Use the node's LSN.
lsn.to_string()
}
};
let branch_name = timeline_name_mappings
.get(&TenantTimelineId::new(tenant_id, endpoint.timeline_id))
.get(&TenantTimelineId::new(tenant_id, node.timeline_id))
.map(|name| name.as_str())
.unwrap_or("?");
table.add_row([
endpoint_id.as_str(),
&endpoint.pg_address.to_string(),
&endpoint.timeline_id.to_string(),
node_name.as_str(),
&node.address.to_string(),
&node.timeline_id.to_string(),
branch_name,
lsn_str.as_str(),
endpoint.status(),
node.status(),
]);
}
@@ -640,10 +596,10 @@ fn handle_endpoint(ep_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<(
.get_one::<String>("branch-name")
.map(|s| s.as_str())
.unwrap_or(DEFAULT_BRANCH_NAME);
let endpoint_id = sub_args
.get_one::<String>("endpoint_id")
.map(String::to_string)
.unwrap_or_else(|| format!("ep-{branch_name}"));
let node_name = sub_args
.get_one::<String>("node")
.map(|node_name| node_name.to_string())
.unwrap_or_else(|| format!("{branch_name}_node"));
let lsn = sub_args
.get_one::<String>("lsn")
@@ -654,78 +610,24 @@ fn handle_endpoint(ep_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<(
.get_branch_timeline_id(branch_name, tenant_id)
.ok_or_else(|| anyhow!("Found no timeline id for branch name '{branch_name}'"))?;
let pg_port: Option<u16> = sub_args.get_one::<u16>("pg-port").copied();
let http_port: Option<u16> = sub_args.get_one::<u16>("http-port").copied();
let port: Option<u16> = sub_args.get_one::<u16>("port").copied();
let pg_version = sub_args
.get_one::<u32>("pg-version")
.copied()
.context("Failed to parse postgres version from the argument string")?;
let hot_standby = sub_args
.get_one::<bool>("hot-standby")
.copied()
.unwrap_or(false);
let pageserver_id =
if let Some(id_str) = sub_args.get_one::<String>("endpoint-pageserver-id") {
NodeId(id_str.parse().context("while parsing pageserver id")?)
} else {
DEFAULT_PAGESERVER_ID
};
let mode = match (lsn, hot_standby) {
(Some(lsn), false) => ComputeMode::Static(lsn),
(None, true) => ComputeMode::Replica,
(None, false) => ComputeMode::Primary,
(Some(_), true) => anyhow::bail!("cannot specify both lsn and hot-standby"),
};
cplane.new_endpoint(
&endpoint_id,
tenant_id,
timeline_id,
pg_port,
http_port,
pg_version,
mode,
pageserver_id,
)?;
cplane.new_node(tenant_id, &node_name, timeline_id, lsn, port, pg_version)?;
}
"start" => {
let pg_port: Option<u16> = sub_args.get_one::<u16>("pg-port").copied();
let http_port: Option<u16> = sub_args.get_one::<u16>("http-port").copied();
let endpoint_id = sub_args
.get_one::<String>("endpoint_id")
.ok_or_else(|| anyhow!("No endpoint ID was provided to start"))?;
let port: Option<u16> = sub_args.get_one::<u16>("port").copied();
let node_name = sub_args
.get_one::<String>("node")
.ok_or_else(|| anyhow!("No node name was provided to start"))?;
let pageserver_id =
if let Some(id_str) = sub_args.get_one::<String>("endpoint-pageserver-id") {
NodeId(id_str.parse().context("while parsing pageserver id")?)
} else {
DEFAULT_PAGESERVER_ID
};
let node = cplane.nodes.get(&(tenant_id, node_name.to_string()));
let remote_ext_config = sub_args.get_one::<String>("remote-ext-config");
// If --safekeepers argument is given, use only the listed safekeeper nodes.
let safekeepers =
if let Some(safekeepers_str) = sub_args.get_one::<String>("safekeepers") {
let mut safekeepers: Vec<NodeId> = Vec::new();
for sk_id in safekeepers_str.split(',').map(str::trim) {
let sk_id = NodeId(u64::from_str(sk_id).map_err(|_| {
anyhow!("invalid node ID \"{sk_id}\" in --safekeepers list")
})?);
safekeepers.push(sk_id);
}
safekeepers
} else {
env.safekeepers.iter().map(|sk| sk.id).collect()
};
let endpoint = cplane.endpoints.get(endpoint_id.as_str());
let ps_conf = env.get_pageserver_conf(pageserver_id)?;
let auth_token = if matches!(ps_conf.pg_auth_type, AuthType::NeonJWT) {
let auth_token = if matches!(env.pageserver.auth_type, AuthType::NeonJWT) {
let claims = Claims::new(Some(tenant_id), Scope::Tenant);
Some(env.generate_auth_token(&claims)?)
@@ -733,23 +635,9 @@ fn handle_endpoint(ep_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<(
None
};
let hot_standby = sub_args
.get_one::<bool>("hot-standby")
.copied()
.unwrap_or(false);
if let Some(endpoint) = endpoint {
match (&endpoint.mode, hot_standby) {
(ComputeMode::Static(_), true) => {
bail!("Cannot start a node in hot standby mode when it is already configured as a static replica")
}
(ComputeMode::Primary, true) => {
bail!("Cannot start a node as a hot standby replica, it is already configured as primary node")
}
_ => {}
}
println!("Starting existing endpoint {endpoint_id}...");
endpoint.start(&auth_token, safekeepers, remote_ext_config)?;
if let Some(node) = node {
println!("Starting existing postgres {node_name}...");
node.start(&auth_token)?;
} else {
let branch_name = sub_args
.get_one::<String>("branch-name")
@@ -769,142 +657,83 @@ fn handle_endpoint(ep_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<(
.get_one::<u32>("pg-version")
.copied()
.context("Failed to `pg-version` from the argument string")?;
let mode = match (lsn, hot_standby) {
(Some(lsn), false) => ComputeMode::Static(lsn),
(None, true) => ComputeMode::Replica,
(None, false) => ComputeMode::Primary,
(Some(_), true) => anyhow::bail!("cannot specify both lsn and hot-standby"),
};
// when used with custom port this results in non obvious behaviour
// port is remembered from first start command, i e
// start --port X
// stop
// start <-- will also use port X even without explicit port argument
println!("Starting new endpoint {endpoint_id} (PostgreSQL v{pg_version}) on timeline {timeline_id} ...");
println!("Starting new postgres (v{pg_version}) {node_name} on timeline {timeline_id} ...");
let ep = cplane.new_endpoint(
endpoint_id,
tenant_id,
timeline_id,
pg_port,
http_port,
pg_version,
mode,
pageserver_id,
)?;
ep.start(&auth_token, safekeepers, remote_ext_config)?;
let node =
cplane.new_node(tenant_id, node_name, timeline_id, lsn, port, pg_version)?;
node.start(&auth_token)?;
}
}
"stop" => {
let endpoint_id = sub_args
.get_one::<String>("endpoint_id")
.ok_or_else(|| anyhow!("No endpoint ID was provided to stop"))?;
let node_name = sub_args
.get_one::<String>("node")
.ok_or_else(|| anyhow!("No node name was provided to stop"))?;
let destroy = sub_args.get_flag("destroy");
let endpoint = cplane
.endpoints
.get(endpoint_id.as_str())
.with_context(|| format!("postgres endpoint {endpoint_id} is not found"))?;
endpoint.stop(destroy)?;
let node = cplane
.nodes
.get(&(tenant_id, node_name.to_string()))
.with_context(|| format!("postgres {node_name} is not found"))?;
node.stop(destroy)?;
}
_ => bail!("Unexpected endpoint subcommand '{sub_name}'"),
_ => bail!("Unexpected pg subcommand '{sub_name}'"),
}
Ok(())
}
fn handle_pageserver(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<()> {
fn get_pageserver(env: &local_env::LocalEnv, args: &ArgMatches) -> Result<PageServerNode> {
let node_id = if let Some(id_str) = args.get_one::<String>("pageserver-id") {
NodeId(id_str.parse().context("while parsing pageserver id")?)
} else {
DEFAULT_PAGESERVER_ID
};
Ok(PageServerNode::from_env(
env,
env.get_pageserver_conf(node_id)?,
))
}
let pageserver = PageServerNode::from_env(env);
match sub_match.subcommand() {
Some(("start", subcommand_args)) => {
if let Err(e) = get_pageserver(env, subcommand_args)?
.start(&pageserver_config_overrides(subcommand_args))
{
Some(("start", start_match)) => {
if let Err(e) = pageserver.start(&pageserver_config_overrides(start_match)) {
eprintln!("pageserver start failed: {e}");
exit(1);
}
}
Some(("stop", subcommand_args)) => {
let immediate = subcommand_args
.get_one::<String>("stop-mode")
.map(|s| s.as_str())
== Some("immediate");
if let Err(e) = get_pageserver(env, subcommand_args)?.stop(immediate) {
eprintln!("pageserver stop failed: {}", e);
exit(1);
}
}
Some(("restart", subcommand_args)) => {
let pageserver = get_pageserver(env, subcommand_args)?;
//TODO what shutdown strategy should we use here?
if let Err(e) = pageserver.stop(false) {
eprintln!("pageserver stop failed: {}", e);
exit(1);
}
if let Err(e) = pageserver.start(&pageserver_config_overrides(subcommand_args)) {
eprintln!("pageserver start failed: {e}");
exit(1);
}
}
Some(("status", subcommand_args)) => {
match get_pageserver(env, subcommand_args)?.check_status() {
Ok(_) => println!("Page server is up and running"),
Err(err) => {
eprintln!("Page server is not available: {}", err);
exit(1);
}
}
}
Some((sub_name, _)) => bail!("Unexpected pageserver subcommand '{}'", sub_name),
None => bail!("no pageserver subcommand provided"),
}
Ok(())
}
fn handle_attachment_service(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<()> {
let svc = AttachmentService::from_env(env);
match sub_match.subcommand() {
Some(("start", _start_match)) => {
if let Err(e) = svc.start() {
eprintln!("start failed: {e}");
exit(1);
}
}
Some(("stop", stop_match)) => {
let immediate = stop_match
.get_one::<String>("stop-mode")
.map(|s| s.as_str())
== Some("immediate");
if let Err(e) = svc.stop(immediate) {
eprintln!("stop failed: {}", e);
if let Err(e) = pageserver.stop(immediate) {
eprintln!("pageserver stop failed: {}", e);
exit(1);
}
}
Some((sub_name, _)) => bail!("Unexpected attachment_service subcommand '{}'", sub_name),
None => bail!("no attachment_service subcommand provided"),
Some(("restart", restart_match)) => {
//TODO what shutdown strategy should we use here?
if let Err(e) = pageserver.stop(false) {
eprintln!("pageserver stop failed: {}", e);
exit(1);
}
if let Err(e) = pageserver.start(&pageserver_config_overrides(restart_match)) {
eprintln!("pageserver start failed: {e}");
exit(1);
}
}
Some(("status", _)) => match PageServerNode::from_env(env).check_status() {
Ok(_) => println!("Page server is up and running"),
Err(err) => {
eprintln!("Page server is not available: {}", err);
exit(1);
}
},
Some((sub_name, _)) => bail!("Unexpected pageserver subcommand '{}'", sub_name),
None => bail!("no pageserver subcommand provided"),
}
Ok(())
}
@@ -917,16 +746,6 @@ fn get_safekeeper(env: &local_env::LocalEnv, id: NodeId) -> Result<SafekeeperNod
}
}
// Get list of options to append to safekeeper command invocation.
fn safekeeper_extra_opts(init_match: &ArgMatches) -> Vec<String> {
init_match
.get_many::<String>("safekeeper-extra-opt")
.into_iter()
.flatten()
.map(|s| s.to_owned())
.collect()
}
fn handle_safekeeper(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<()> {
let (sub_name, sub_args) = match sub_match.subcommand() {
Some(safekeeper_command_data) => safekeeper_command_data,
@@ -943,9 +762,7 @@ fn handle_safekeeper(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> Resul
match sub_name {
"start" => {
let extra_opts = safekeeper_extra_opts(sub_args);
if let Err(e) = safekeeper.start(extra_opts) {
if let Err(e) = safekeeper.start() {
eprintln!("safekeeper start failed: {}", e);
exit(1);
}
@@ -970,8 +787,7 @@ fn handle_safekeeper(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> Resul
exit(1);
}
let extra_opts = safekeeper_extra_opts(sub_args);
if let Err(e) = safekeeper.start(extra_opts) {
if let Err(e) = safekeeper.start() {
eprintln!("safekeeper start failed: {}", e);
exit(1);
}
@@ -985,32 +801,20 @@ fn handle_safekeeper(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> Resul
}
fn handle_start_all(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> anyhow::Result<()> {
// Endpoints are not started automatically
// Postgres nodes are not started automatically
broker::start_broker_process(env)?;
// Only start the attachment service if the pageserver is configured to need it
if env.control_plane_api.is_some() {
let attachment_service = AttachmentService::from_env(env);
if let Err(e) = attachment_service.start() {
eprintln!("attachment_service start failed: {:#}", e);
try_stop_all(env, true);
exit(1);
}
}
for ps_conf in &env.pageservers {
let pageserver = PageServerNode::from_env(env, ps_conf);
if let Err(e) = pageserver.start(&pageserver_config_overrides(sub_match)) {
eprintln!("pageserver {} start failed: {:#}", ps_conf.id, e);
try_stop_all(env, true);
exit(1);
}
let pageserver = PageServerNode::from_env(env);
if let Err(e) = pageserver.start(&pageserver_config_overrides(sub_match)) {
eprintln!("pageserver {} start failed: {:#}", env.pageserver.id, e);
try_stop_all(env, true);
exit(1);
}
for node in env.safekeepers.iter() {
let safekeeper = SafekeeperNode::from_env(env, node);
if let Err(e) = safekeeper.start(vec![]) {
if let Err(e) = safekeeper.start() {
eprintln!("safekeeper {} start failed: {:#}", safekeeper.id, e);
try_stop_all(env, false);
exit(1);
@@ -1029,10 +833,12 @@ fn handle_stop_all(sub_match: &ArgMatches, env: &local_env::LocalEnv) -> Result<
}
fn try_stop_all(env: &local_env::LocalEnv, immediate: bool) {
// Stop all endpoints
let pageserver = PageServerNode::from_env(env);
// Stop all compute nodes
match ComputeControlPlane::load(env.clone()) {
Ok(cplane) => {
for (_k, node) in cplane.endpoints {
for (_k, node) in cplane.nodes {
if let Err(e) = node.stop(false) {
eprintln!("postgres stop failed: {e:#}");
}
@@ -1043,11 +849,8 @@ fn try_stop_all(env: &local_env::LocalEnv, immediate: bool) {
}
}
for ps_conf in &env.pageservers {
let pageserver = PageServerNode::from_env(env, ps_conf);
if let Err(e) = pageserver.stop(immediate) {
eprintln!("pageserver {} stop failed: {:#}", ps_conf.id, e);
}
if let Err(e) = pageserver.stop(immediate) {
eprintln!("pageserver {} stop failed: {:#}", env.pageserver.id, e);
}
for node in env.safekeepers.iter() {
@@ -1060,13 +863,6 @@ fn try_stop_all(env: &local_env::LocalEnv, immediate: bool) {
if let Err(e) = broker::stop_broker_process(env) {
eprintln!("neon broker stop failed: {e:#}");
}
if env.control_plane_api.is_some() {
let attachment_service = AttachmentService::from_env(env);
if let Err(e) = attachment_service.stop(immediate) {
eprintln!("attachment service stop failed: {e:#}");
}
}
}
fn cli() -> Command {
@@ -1075,30 +871,10 @@ fn cli() -> Command {
.help("Name of the branch to be created or used as an alias for other services")
.required(false);
let endpoint_id_arg = Arg::new("endpoint_id")
.help("Postgres endpoint id")
.required(false);
let pg_node_arg = Arg::new("node").help("Postgres node name").required(false);
let safekeeper_id_arg = Arg::new("id").help("safekeeper id").required(false);
// --id, when using a pageserver command
let pageserver_id_arg = Arg::new("pageserver-id")
.long("id")
.help("pageserver id")
.required(false);
// --pageserver-id when using a non-pageserver command
let endpoint_pageserver_id_arg = Arg::new("endpoint-pageserver-id")
.long("pageserver-id")
.required(false);
let safekeeper_extra_opt_arg = Arg::new("safekeeper-extra-opt")
.short('e')
.long("safekeeper-extra-opt")
.num_args(1)
.action(ArgAction::Append)
.help("Additional safekeeper invocation options, e.g. -e=--http-auth-public-key-path=foo")
.required(false);
let tenant_id_arg = Arg::new("tenant-id")
.long("tenant-id")
.help("Tenant id. Represented as a hexadecimal string 32 symbols length")
@@ -1116,22 +892,11 @@ fn cli() -> Command {
.value_parser(value_parser!(u32))
.default_value(DEFAULT_PG_VERSION);
let pg_port_arg = Arg::new("pg-port")
.long("pg-port")
let port_arg = Arg::new("port")
.long("port")
.required(false)
.value_parser(value_parser!(u16))
.value_name("pg-port");
let http_port_arg = Arg::new("http-port")
.long("http-port")
.required(false)
.value_parser(value_parser!(u16))
.value_name("http-port");
let safekeepers_arg = Arg::new("safekeepers")
.long("safekeepers")
.required(false)
.value_name("safekeepers");
.value_name("port");
let stop_mode_arg = Arg::new("stop-mode")
.short('m')
@@ -1148,30 +913,11 @@ fn cli() -> Command {
.help("Additional pageserver's configuration options or overrides, refer to pageserver's 'config-override' CLI parameter docs for more")
.required(false);
let remote_ext_config_args = Arg::new("remote-ext-config")
.long("remote-ext-config")
.num_args(1)
.help("Configure the S3 bucket that we search for extensions in.")
.required(false);
let lsn_arg = Arg::new("lsn")
.long("lsn")
.help("Specify Lsn on the timeline to start from. By default, end of the timeline would be used.")
.required(false);
let hot_standby_arg = Arg::new("hot-standby")
.value_parser(value_parser!(bool))
.long("hot-standby")
.help("If set, the node will be a hot replica on the specified timeline")
.required(false);
let force_arg = Arg::new("force")
.value_parser(value_parser!(bool))
.long("force")
.action(ArgAction::SetTrue)
.help("Force initialization even if the repository is not empty")
.required(false);
Command::new("Neon CLI")
.arg_required_else_help(true)
.version(GIT_VERSION)
@@ -1187,7 +933,6 @@ fn cli() -> Command {
.value_name("config"),
)
.arg(pg_version_arg.clone())
.arg(force_arg)
)
.subcommand(
Command::new("timeline")
@@ -1255,24 +1000,10 @@ fn cli() -> Command {
.arg_required_else_help(true)
.about("Manage pageserver")
.subcommand(Command::new("status"))
.arg(pageserver_id_arg.clone())
.subcommand(Command::new("start").about("Start local pageserver")
.arg(pageserver_id_arg.clone())
.arg(pageserver_config_args.clone()))
.subcommand(Command::new("stop").about("Stop local pageserver")
.arg(pageserver_id_arg.clone())
.arg(stop_mode_arg.clone()))
.subcommand(Command::new("restart").about("Restart local pageserver")
.arg(pageserver_id_arg.clone())
.arg(pageserver_config_args.clone()))
)
.subcommand(
Command::new("attachment_service")
.arg_required_else_help(true)
.about("Manage attachment_service")
.subcommand(Command::new("start").about("Start local pageserver").arg(pageserver_config_args.clone()))
.subcommand(Command::new("stop").about("Stop local pageserver")
.arg(stop_mode_arg.clone()))
.subcommand(Command::new("restart").about("Restart local pageserver").arg(pageserver_config_args.clone()))
)
.subcommand(
Command::new("safekeeper")
@@ -1281,7 +1012,6 @@ fn cli() -> Command {
.subcommand(Command::new("start")
.about("Start local safekeeper")
.arg(safekeeper_id_arg.clone())
.arg(safekeeper_extra_opt_arg.clone())
)
.subcommand(Command::new("stop")
.about("Stop local safekeeper")
@@ -1292,49 +1022,40 @@ fn cli() -> Command {
.about("Restart local safekeeper")
.arg(safekeeper_id_arg)
.arg(stop_mode_arg.clone())
.arg(safekeeper_extra_opt_arg)
)
)
.subcommand(
Command::new("endpoint")
Command::new("pg")
.arg_required_else_help(true)
.about("Manage postgres instances")
.subcommand(Command::new("list").arg(tenant_id_arg.clone()))
.subcommand(Command::new("create")
.about("Create a compute endpoint")
.arg(endpoint_id_arg.clone())
.about("Create a postgres compute node")
.arg(pg_node_arg.clone())
.arg(branch_name_arg.clone())
.arg(tenant_id_arg.clone())
.arg(lsn_arg.clone())
.arg(pg_port_arg.clone())
.arg(http_port_arg.clone())
.arg(endpoint_pageserver_id_arg.clone())
.arg(port_arg.clone())
.arg(
Arg::new("config-only")
.help("Don't do basebackup, create endpoint directory with only config files")
.help("Don't do basebackup, create compute node with only config files")
.long("config-only")
.required(false))
.arg(pg_version_arg.clone())
.arg(hot_standby_arg.clone())
)
.subcommand(Command::new("start")
.about("Start postgres.\n If the endpoint doesn't exist yet, it is created.")
.arg(endpoint_id_arg.clone())
.about("Start a postgres compute node.\n This command actually creates new node from scratch, but preserves existing config files")
.arg(pg_node_arg.clone())
.arg(tenant_id_arg.clone())
.arg(branch_name_arg)
.arg(timeline_id_arg)
.arg(lsn_arg)
.arg(pg_port_arg)
.arg(http_port_arg)
.arg(endpoint_pageserver_id_arg.clone())
.arg(port_arg)
.arg(pg_version_arg)
.arg(hot_standby_arg)
.arg(safekeepers_arg)
.arg(remote_ext_config_args)
)
.subcommand(
Command::new("stop")
.arg(endpoint_id_arg)
.arg(pg_node_arg)
.arg(tenant_id_arg)
.arg(
Arg::new("destroy")
@@ -1346,13 +1067,6 @@ fn cli() -> Command {
)
)
// Obsolete old name for 'endpoint'. We now just print an error if it's used.
.subcommand(
Command::new("pg")
.hide(true)
.arg(Arg::new("ignore-rest").allow_hyphen_values(true).num_args(0..).required(false))
.trailing_var_arg(true)
)
.subcommand(
Command::new("start")
.about("Start page server and safekeepers")

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