Compare commits

..

8 Commits

Author SHA1 Message Date
Bojan Serafimov
edc77e8a24 Add pyo3 prototype 2022-08-30 11:28:22 -04:00
Bojan Serafimov
324c09d19f Cleanup 2022-08-18 15:17:30 -04:00
Bojan Serafimov
1501dbd5a5 Cleanup 2022-08-18 15:16:14 -04:00
Bojan Serafimov
4e91ff31ca Fmt 2022-08-18 13:20:01 -04:00
Bojan Serafimov
fe1b471cfc Cleanup 2022-08-18 13:14:05 -04:00
Bojan Serafimov
3e0b57e766 Convert bin to lib 2022-08-18 12:41:46 -04:00
Bojan Serafimov
7bff7c4014 Add library 2022-08-18 12:40:14 -04:00
Bojan Serafimov
11a1f2a1d8 Initial experiment 2022-08-18 12:27:43 -04:00
560 changed files with 30765 additions and 98818 deletions

View File

@@ -11,6 +11,3 @@ opt-level = 3
[profile.dev]
# Turn on a small amount of optimization in Development mode.
opt-level = 1
[alias]
build_testing = ["build", "--features", "testing"]

View File

@@ -1,22 +1,18 @@
*
**/.git/
**/__pycache__
**/.pytest_cache
!rust-toolchain.toml
!Cargo.toml
!Cargo.lock
!Makefile
.git
target
tmp_check
tmp_install
tmp_check_cli
test_output
.vscode
.neon
integration_tests/.neon
.mypy_cache
Dockerfile
.dockerignore
!.cargo/
!.config/
!control_plane/
!compute_tools/
!libs/
!pageserver/
!pgxn/
!proxy/
!safekeeper/
!storage_broker/
!vendor/postgres-v14/
!vendor/postgres-v15/
!workspace_hack/
!neon_local/
!scripts/ninstall.sh

View File

@@ -1 +0,0 @@
4c2bb43775947775401cbb9d774823c5723a91f8

View File

@@ -1,23 +0,0 @@
---
name: Bug Template
about: Used for describing bugs
title: ''
labels: t/bug
assignees: ''
---
## Steps to reproduce
## Expected result
## Actual result
## Environment
## Logs, links
-

View File

@@ -1,25 +0,0 @@
---
name: Epic Template
about: A set of related tasks contributing towards specific outcome, comprising of
more than 1 week of work.
title: 'Epic: '
labels: t/Epic
assignees: ''
---
## Motivation
## DoD
## Implementation ideas
## Tasks
- [ ]
## Other related tasks and Epics
-

View File

@@ -1,20 +0,0 @@
## Release 202Y-MM-DD
**NB: this PR must be merged only by 'Create a merge commit'!**
### Checklist when preparing for release
- [ ] Read or refresh [the release flow guide](https://github.com/neondatabase/cloud/wiki/Release:-general-flow)
- [ ] Ask in the [cloud Slack channel](https://neondb.slack.com/archives/C033A2WE6BZ) that you are going to rollout the release. Any blockers?
- [ ] Does this release contain any db migrations? Destructive ones? What is the rollback plan?
<!-- List everything that should be done **before** release, any issues / setting changes / etc -->
### Checklist after release
- [ ] 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)
- [ ] Check [recent operation failures](https://console.neon.tech/admin/operations?action=create_timeline%2Cstart_compute%2Cstop_compute%2Csuspend_compute%2Capply_config%2Cdelete_timeline%2Cdelete_tenant%2Ccreate_branch%2Ccheck_availability&sort=updated_at&order=desc&had_retries=some)
- [ ] Check [cloud SLO dashboard](https://neonprod.grafana.net/d/_oWcBMJ7k/cloud-slos?orgId=1)
- [ ] Check [compute startup metrics dashboard](https://neonprod.grafana.net/d/5OkYJEmVz/compute-startup-time)
<!-- List everything that should be done **after** release, any admin UI configuration / Grafana dashboard / alert changes / setting changes / etc -->

View File

@@ -1,232 +0,0 @@
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

@@ -12,9 +12,6 @@ inputs:
description: "Allow to skip if file doesn't exist, fail otherwise"
default: false
required: false
prefix:
description: "S3 prefix. Default is '${GITHUB_RUN_ID}/${GITHUB_RUN_ATTEMPT}'"
required: false
runs:
using: "composite"
@@ -26,23 +23,23 @@ runs:
TARGET: ${{ inputs.path }}
ARCHIVE: /tmp/downloads/${{ inputs.name }}.tar.zst
SKIP_IF_DOES_NOT_EXIST: ${{ inputs.skip-if-does-not-exist }}
PREFIX: artifacts/${{ inputs.prefix || format('{0}/{1}', github.run_id, github.run_attempt) }}
run: |
BUCKET=neon-github-public-dev
PREFIX=artifacts/${GITHUB_RUN_ID}
FILENAME=$(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} | 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' >> $GITHUB_OUTPUT
echo '::set-output name=SKIPPED::true'
exit 0
else
echo 2>&1 "Neither s3://${BUCKET}/${PREFIX}/${FILENAME} nor its version from previous attempts exist"
echo 2>&1 "Neither s3://${BUCKET}/${PREFIX}/${GITHUB_RUN_ATTEMPT}/${FILENAME} nor its version from previous attempts exist"
exit 1
fi
fi
echo 'SKIPPED=false' >> $GITHUB_OUTPUT
echo '::set-output name=SKIPPED::false'
mkdir -p $(dirname $ARCHIVE)
time aws s3 cp --only-show-errors s3://${BUCKET}/${S3_KEY} ${ARCHIVE}

View File

@@ -1,138 +0,0 @@
name: 'Create Branch'
description: 'Create Branch using API'
inputs:
api_key:
desctiption: 'Neon API key'
required: true
project_id:
desctiption: 'ID of the Project to create Branch in'
required: true
api_host:
desctiption: 'Neon API host'
default: console.stage.neon.tech
outputs:
dsn:
description: 'Created Branch DSN (for main database)'
value: ${{ steps.change-password.outputs.dsn }}
branch_id:
description: 'Created Branch ID'
value: ${{ steps.create-branch.outputs.branch_id }}
runs:
using: "composite"
steps:
- name: Create New Branch
id: create-branch
shell: bash -euxo pipefail {0}
run: |
for i in $(seq 1 10); do
branch=$(curl \
"https://${API_HOST}/api/v2/projects/${PROJECT_ID}/branches" \
--header "Accept: application/json" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${API_KEY}" \
--data "{
\"branch\": {
\"name\": \"Created by actions/neon-branch-create; GITHUB_RUN_ID=${GITHUB_RUN_ID} at $(date +%s)\"
},
\"endpoints\": [
{
\"type\": \"read_write\"
}
]
}")
if [ -z "${branch}" ]; then
sleep 1
continue
fi
branch_id=$(echo $branch | jq --raw-output '.branch.id')
if [ "${branch_id}" == "null" ]; then
sleep 1
continue
fi
break
done
if [ -z "${branch_id}" ] || [ "${branch_id}" == "null" ]; then
echo 2>&1 "Failed to create branch after 10 attempts, the latest response was: ${branch}"
exit 1
fi
branch_id=$(echo $branch | jq --raw-output '.branch.id')
echo "branch_id=${branch_id}" >> $GITHUB_OUTPUT
host=$(echo $branch | jq --raw-output '.endpoints[0].host')
echo "host=${host}" >> $GITHUB_OUTPUT
env:
API_HOST: ${{ inputs.api_host }}
API_KEY: ${{ inputs.api_key }}
PROJECT_ID: ${{ inputs.project_id }}
- name: Get Role name
id: role-name
shell: bash -euxo pipefail {0}
run: |
roles=$(curl \
"https://${API_HOST}/api/v2/projects/${PROJECT_ID}/branches/${BRANCH_ID}/roles" \
--fail \
--header "Accept: application/json" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${API_KEY}"
)
role_name=$(echo $roles | jq --raw-output '.roles[] | select(.protected == false) | .name')
echo "role_name=${role_name}" >> $GITHUB_OUTPUT
env:
API_HOST: ${{ inputs.api_host }}
API_KEY: ${{ inputs.api_key }}
PROJECT_ID: ${{ inputs.project_id }}
BRANCH_ID: ${{ steps.create-branch.outputs.branch_id }}
- name: Change Password
id: change-password
# A shell without `set -x` to not to expose password/dsn in logs
shell: bash -euo pipefail {0}
run: |
for i in $(seq 1 10); do
reset_password=$(curl \
"https://${API_HOST}/api/v2/projects/${PROJECT_ID}/branches/${BRANCH_ID}/roles/${ROLE_NAME}/reset_password" \
--request POST \
--header "Accept: application/json" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${API_KEY}"
)
if [ -z "${reset_password}" ]; then
sleep 1
continue
fi
password=$(echo $reset_password | jq --raw-output '.role.password')
if [ "${password}" == "null" ]; then
sleep 1
continue
fi
echo "::add-mask::${password}"
break
done
if [ -z "${password}" ] || [ "${password}" == "null" ]; then
echo 2>&1 "Failed to reset password after 10 attempts, the latest response was: ${reset_password}"
exit 1
fi
dsn="postgres://${ROLE_NAME}:${password}@${HOST}/neondb"
echo "::add-mask::${dsn}"
echo "dsn=${dsn}" >> $GITHUB_OUTPUT
env:
API_HOST: ${{ inputs.api_host }}
API_KEY: ${{ inputs.api_key }}
PROJECT_ID: ${{ inputs.project_id }}
BRANCH_ID: ${{ steps.create-branch.outputs.branch_id }}
ROLE_NAME: ${{ steps.role-name.outputs.role_name }}
HOST: ${{ steps.create-branch.outputs.host }}

View File

@@ -1,58 +0,0 @@
name: 'Delete Branch'
description: 'Delete Branch using API'
inputs:
api_key:
desctiption: 'Neon API key'
required: true
project_id:
desctiption: 'ID of the Project which should be deleted'
required: true
branch_id:
desctiption: 'ID of the branch to delete'
required: true
api_host:
desctiption: 'Neon API host'
default: console.stage.neon.tech
runs:
using: "composite"
steps:
- name: Delete Branch
# Do not try to delete a branch if .github/actions/neon-project-create
# or .github/actions/neon-branch-create failed before
if: ${{ inputs.project_id != '' && inputs.branch_id != '' }}
shell: bash -euxo pipefail {0}
run: |
for i in $(seq 1 10); do
deleted_branch=$(curl \
"https://${API_HOST}/api/v2/projects/${PROJECT_ID}/branches/${BRANCH_ID}" \
--request DELETE \
--header "Accept: application/json" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${API_KEY}"
)
if [ -z "${deleted_branch}" ]; then
sleep 1
continue
fi
branch_id=$(echo $deleted_branch | jq --raw-output '.branch.id')
if [ "${branch_id}" == "null" ]; then
sleep 1
continue
fi
break
done
if [ -z "${branch_id}" ] || [ "${branch_id}" == "null" ]; then
echo 2>&1 "Failed to delete branch after 10 attempts, the latest response was: ${deleted_branch}"
exit 1
fi
env:
API_HOST: ${{ inputs.api_host }}
API_KEY: ${{ inputs.api_key }}
PROJECT_ID: ${{ inputs.project_id }}
BRANCH_ID: ${{ inputs.branch_id }}

View File

@@ -1,64 +0,0 @@
name: 'Create Neon Project'
description: 'Create Neon Project using API'
inputs:
api_key:
desctiption: 'Neon API key'
required: true
region_id:
desctiption: 'Region ID, if not set the project will be created in the default region'
default: aws-us-east-2
postgres_version:
desctiption: 'Postgres version; default is 15'
default: 15
api_host:
desctiption: 'Neon API host'
default: console.stage.neon.tech
outputs:
dsn:
description: 'Created Project DSN (for main database)'
value: ${{ steps.create-neon-project.outputs.dsn }}
project_id:
description: 'Created Project ID'
value: ${{ steps.create-neon-project.outputs.project_id }}
runs:
using: "composite"
steps:
- name: Create Neon Project
id: create-neon-project
# A shell without `set -x` to not to expose password/dsn in logs
shell: bash -euo pipefail {0}
run: |
project=$(curl \
"https://${API_HOST}/api/v2/projects" \
--fail \
--header "Accept: application/json" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${API_KEY}" \
--data "{
\"project\": {
\"name\": \"Created by actions/neon-project-create; GITHUB_RUN_ID=${GITHUB_RUN_ID}\",
\"pg_version\": ${POSTGRES_VERSION},
\"region_id\": \"${REGION_ID}\",
\"settings\": { }
}
}")
# Mask password
echo "::add-mask::$(echo $project | jq --raw-output '.roles[] | select(.name != "web_access") | .password')"
dsn=$(echo $project | jq --raw-output '.connection_uris[0].connection_uri')
echo "::add-mask::${dsn}"
echo "dsn=${dsn}" >> $GITHUB_OUTPUT
project_id=$(echo $project | jq --raw-output '.project.id')
echo "project_id=${project_id}" >> $GITHUB_OUTPUT
echo "Project ${project_id} has been created"
env:
API_HOST: ${{ inputs.api_host }}
API_KEY: ${{ inputs.api_key }}
REGION_ID: ${{ inputs.region_id }}
POSTGRES_VERSION: ${{ inputs.postgres_version }}

View File

@@ -1,35 +0,0 @@
name: 'Delete Neon Project'
description: 'Delete Neon Project using API'
inputs:
api_key:
desctiption: 'Neon API key'
required: true
project_id:
desctiption: 'ID of the Project to delete'
required: true
api_host:
desctiption: 'Neon API host'
default: console.stage.neon.tech
runs:
using: "composite"
steps:
- name: Delete Neon Project
# Do not try to delete a project if .github/actions/neon-project-create failed before
if: ${{ inputs.project_id != '' }}
shell: bash -euxo pipefail {0}
run: |
curl \
"https://${API_HOST}/api/v2/projects/${PROJECT_ID}" \
--fail \
--request DELETE \
--header "Accept: application/json" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${API_KEY}"
echo "Project ${PROJECT_ID} has been deleted"
env:
API_HOST: ${{ inputs.api_host }}
API_KEY: ${{ inputs.api_key }}
PROJECT_ID: ${{ inputs.project_id }}

View File

@@ -3,7 +3,10 @@ description: 'Runs a Neon python test set, performing all the required preparati
inputs:
build_type:
description: 'Type of Rust (neon) and C (postgres) builds. Must be "release" or "debug", or "remote" for the remote cluster'
description: 'Type of Rust (neon) and C (postgres) builds. Must be "release" or "debug".'
required: true
rust_toolchain:
description: 'Rust toolchain version to fetch the caches'
required: true
test_selection:
description: 'A python test suite to run'
@@ -21,7 +24,7 @@ inputs:
required: false
default: 'true'
save_perf_report:
description: 'Whether to upload the performance report, if true PERF_TEST_RESULT_CONNSTR env variable should be set'
description: 'Whether to upload the performance report'
required: false
default: 'false'
run_with_real_s3:
@@ -49,28 +52,11 @@ runs:
using: "composite"
steps:
- name: Get Neon artifact
if: inputs.build_type != 'remote'
uses: ./.github/actions/download
with:
name: neon-${{ runner.os }}-${{ inputs.build_type }}-artifact
name: neon-${{ runner.os }}-${{ inputs.build_type }}-${{ inputs.rust_toolchain }}-artifact
path: /tmp/neon
- name: Download Neon binaries for the previous release
if: inputs.build_type != 'remote'
uses: ./.github/actions/download
with:
name: neon-${{ runner.os }}-${{ inputs.build_type }}-artifact
path: /tmp/neon-previous
prefix: latest
- name: Download compatibility snapshot for Postgres 14
if: inputs.build_type != 'remote'
uses: ./.github/actions/download
with:
name: compatibility-snapshot-${{ inputs.build_type }}-pg14
path: /tmp/compatibility_snapshot_pg14
prefix: latest
- name: Checkout
if: inputs.needs_postgres_source == 'true'
uses: actions/checkout@v3
@@ -92,27 +78,16 @@ runs:
- name: Run pytest
env:
NEON_BIN: /tmp/neon/bin
COMPATIBILITY_NEON_BIN: /tmp/neon-previous/bin
COMPATIBILITY_POSTGRES_DISTRIB_DIR: /tmp/neon-previous/pg_install
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
TEST_OUTPUT: /tmp/test_output
# this variable will be embedded in perf test report
# and is needed to distinguish different environments
PLATFORM: github-actions-selfhosted
BUILD_TYPE: ${{ inputs.build_type }}
AWS_ACCESS_KEY_ID: ${{ inputs.real_s3_access_key_id }}
AWS_SECRET_ACCESS_KEY: ${{ inputs.real_s3_secret_access_key }}
COMPATIBILITY_SNAPSHOT_DIR: /tmp/compatibility_snapshot_pg14
ALLOW_BACKWARD_COMPATIBILITY_BREAKAGE: contains(github.event.pull_request.labels.*.name, 'backward compatibility breakage')
ALLOW_FORWARD_COMPATIBILITY_BREAKAGE: contains(github.event.pull_request.labels.*.name, 'forward compatibility breakage')
shell: bash -euxo pipefail {0}
run: |
# PLATFORM will be embedded in the perf test report
# and it is needed to distinguish different environments
export PLATFORM=${PLATFORM:-github-actions-selfhosted}
export POSTGRES_DISTRIB_DIR=${POSTGRES_DISTRIB_DIR:-/tmp/neon/pg_install}
export DEFAULT_PG_VERSION=${DEFAULT_PG_VERSION:-14}
if [ "${BUILD_TYPE}" = "remote" ]; then
export REMOTE_ENV=1
fi
PERF_REPORT_DIR="$(realpath test_runner/perf-report-local)"
rm -rf $PERF_REPORT_DIR
@@ -123,12 +98,7 @@ runs:
exit 1
fi
if [[ "${{ inputs.run_in_parallel }}" == "true" ]]; then
# -n8 uses eight processes to run tests via pytest-xdist
EXTRA_PARAMS="-n8 $EXTRA_PARAMS"
# --dist=loadgroup points tests marked with @pytest.mark.xdist_group
# to the same worker to make @pytest.mark.order work with xdist
EXTRA_PARAMS="--dist=loadgroup $EXTRA_PARAMS"
EXTRA_PARAMS="-n4 $EXTRA_PARAMS"
fi
if [[ "${{ inputs.run_with_real_s3 }}" == "true" ]]; then
@@ -139,21 +109,16 @@ runs:
fi
if [[ "${{ inputs.save_perf_report }}" == "true" ]]; then
mkdir -p "$PERF_REPORT_DIR"
EXTRA_PARAMS="--out-dir $PERF_REPORT_DIR $EXTRA_PARAMS"
if [[ "$GITHUB_REF" == "refs/heads/main" ]]; then
mkdir -p "$PERF_REPORT_DIR"
EXTRA_PARAMS="--out-dir $PERF_REPORT_DIR $EXTRA_PARAMS"
fi
fi
if [[ "${{ inputs.build_type }}" == "debug" ]]; then
cov_prefix=(scripts/coverage "--profraw-prefix=$GITHUB_JOB" --dir=/tmp/coverage run)
elif [[ "${{ inputs.build_type }}" == "release" ]]; then
cov_prefix=()
else
cov_prefix=()
fi
# Wake up the cluster if we use remote neon instance
if [ "${{ inputs.build_type }}" = "remote" ] && [ -n "${BENCHMARK_CONNSTR}" ]; then
${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin/psql ${BENCHMARK_CONNSTR} -c "SELECT version();"
fi
# Run the tests.
@@ -163,36 +128,35 @@ runs:
# --verbose prints name of each test (helpful when there are
# multiple tests in one file)
# -rA prints summary in the end
# -n4 uses four processes to run tests via pytest-xdist
# -s is not used to prevent pytest from capturing output, because tests are running
# in parallel and logs are mixed between different tests
#
mkdir -p $TEST_OUTPUT/allure/results
"${cov_prefix[@]}" ./scripts/pytest \
--junitxml=$TEST_OUTPUT/junit.xml \
--alluredir=$TEST_OUTPUT/allure/results \
--tb=short \
--verbose \
-m "not remote_cluster" \
-rA $TEST_SELECTION $EXTRA_PARAMS
if [[ "${{ inputs.save_perf_report }}" == "true" ]]; then
export REPORT_FROM="$PERF_REPORT_DIR"
export REPORT_TO="$PLATFORM"
scripts/generate_and_push_perf_report.sh
if [[ "$GITHUB_REF" == "refs/heads/main" ]]; then
export REPORT_FROM="$PERF_REPORT_DIR"
export REPORT_TO=local
scripts/generate_and_push_perf_report.sh
fi
fi
- name: Upload compatibility snapshot for Postgres 14
if: github.ref_name == 'release'
- name: Delete all data but logs
shell: bash -euxo pipefail {0}
if: always()
run: |
du -sh /tmp/test_output/*
find /tmp/test_output -type f ! -name "*.log" ! -name "regression.diffs" ! -name "junit.xml" ! -name "*.filediff" ! -name "*.stdout" ! -name "*.stderr" ! -name "flamegraph.svg" ! -name "*.metrics" -delete
du -sh /tmp/test_output/*
- name: Upload python test logs
if: always()
uses: ./.github/actions/upload
with:
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: Create Allure report
if: success() || failure()
uses: ./.github/actions/allure-report
with:
action: store
build_type: ${{ inputs.build_type }}
test_selection: ${{ inputs.test_selection }}
name: python-test-${{ inputs.test_selection }}-${{ runner.os }}-${{ inputs.build_type }}-${{ inputs.rust_toolchain }}-logs
path: /tmp/test_output/

View File

@@ -7,9 +7,6 @@ inputs:
path:
description: "A directory or file to upload"
required: true
prefix:
description: "S3 prefix. Default is '${GITHUB_RUN_ID}/${GITHUB_RUN_ATTEMPT}'"
required: false
runs:
using: "composite"
@@ -45,14 +42,14 @@ runs:
env:
SOURCE: ${{ inputs.path }}
ARCHIVE: /tmp/uploads/${{ inputs.name }}.tar.zst
PREFIX: artifacts/${{ inputs.prefix || format('{0}/{1}', github.run_id, github.run_attempt) }}
run: |
BUCKET=neon-github-public-dev
PREFIX=artifacts/${GITHUB_RUN_ID}
FILENAME=$(basename $ARCHIVE)
FILESIZE=$(du -sh ${ARCHIVE} | cut -f1)
time aws s3 mv --only-show-errors ${ARCHIVE} s3://${BUCKET}/${PREFIX}/${FILENAME}
time aws s3 mv --only-show-errors ${ARCHIVE} s3://${BUCKET}/${PREFIX}/${GITHUB_RUN_ATTEMPT}/${FILENAME}
# Ref https://docs.github.com/en/actions/using-workflows/workflow-commands-for-github-actions#adding-a-job-summary
echo "[${FILENAME}](https://${BUCKET}.s3.amazonaws.com/${PREFIX}/${FILENAME}) ${FILESIZE}" >> ${GITHUB_STEP_SUMMARY}
echo "[${FILENAME}](https://${BUCKET}.s3.amazonaws.com/${PREFIX}/${GITHUB_RUN_ATTEMPT}/${FILENAME}) ${FILESIZE}" >> ${GITHUB_STEP_SUMMARY}

View File

@@ -1,5 +1,4 @@
zenith_install.tar.gz
.zenith_current_version
neon_install.tar.gz
.neon_current_version
collections/*
!collections/.keep

View File

View File

@@ -1,7 +1,7 @@
- name: Upload Neon binaries
hosts: storage
gather_facts: False
remote_user: "{{ remote_user }}"
remote_user: admin
tasks:
@@ -14,8 +14,7 @@
- safekeeper
- name: inform about versions
debug:
msg: "Version to deploy - {{ current_version }}"
debug: msg="Version to deploy - {{ current_version }}"
tags:
- pageserver
- safekeeper
@@ -36,7 +35,7 @@
- name: Deploy pageserver
hosts: pageservers
gather_facts: False
remote_user: "{{ remote_user }}"
remote_user: admin
tasks:
@@ -59,34 +58,20 @@
creates: "/storage/pageserver/data/tenants"
environment:
NEON_REPO_DIR: "/storage/pageserver/data"
LD_LIBRARY_PATH: "/usr/local/v14/lib"
LD_LIBRARY_PATH: "/usr/local/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
- name: update remote storage (s3) config
lineinfile:
path: /storage/pageserver/data/pageserver.toml
line: "{{ item }}"
loop:
- "[remote_storage]"
- "bucket_name = '{{ bucket_name }}'"
- "bucket_region = '{{ bucket_region }}'"
- "prefix_in_bucket = '{{ inventory_hostname }}'"
become: true
tags:
- pageserver
@@ -124,7 +109,7 @@
- name: Deploy safekeeper
hosts: safekeepers
gather_facts: False
remote_user: "{{ remote_user }}"
remote_user: admin
tasks:
@@ -147,7 +132,7 @@
creates: "/storage/safekeeper/data/safekeeper.id"
environment:
NEON_REPO_DIR: "/storage/safekeeper/data"
LD_LIBRARY_PATH: "/usr/local/v14/lib"
LD_LIBRARY_PATH: "/usr/local/lib"
become: true
tags:
- safekeeper

View File

@@ -21,16 +21,10 @@ 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 cp ${ID}:/usr/local/bin/postgres neon_install/bin/
docker rm -vf ${ID}
# store version to file (for ansible playbooks) and create binaries tarball

20
.github/ansible/neon-stress.hosts vendored Normal file
View File

@@ -0,0 +1,20 @@
[pageservers]
neon-stress-ps-1 console_region_id=1
neon-stress-ps-2 console_region_id=1
[safekeepers]
neon-stress-sk-1 console_region_id=1
neon-stress-sk-2 console_region_id=1
neon-stress-sk-3 console_region_id=1
[storage:children]
pageservers
safekeepers
[storage:vars]
env_name = neon-stress
console_mgmt_base_url = http://neon-stress-console.local
bucket_name = neon-storage-ireland
bucket_region = eu-west-1
etcd_endpoints = etcd-stress.local:2379
safekeeper_enable_s3_offload = false

View File

@@ -1,36 +0,0 @@
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
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

@@ -1,36 +0,0 @@
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
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

@@ -1,37 +0,0 @@
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
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

@@ -1,39 +0,0 @@
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
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

20
.github/ansible/production.hosts vendored Normal file
View File

@@ -0,0 +1,20 @@
[pageservers]
#zenith-1-ps-1 console_region_id=1
zenith-1-ps-2 console_region_id=1
zenith-1-ps-3 console_region_id=1
[safekeepers]
zenith-1-sk-1 console_region_id=1
zenith-1-sk-2 console_region_id=1
zenith-1-sk-3 console_region_id=1
[storage:children]
pageservers
safekeepers
[storage:vars]
env_name = prod-1
console_mgmt_base_url = http://console-release.local
bucket_name = zenith-storage-oregon
bucket_region = us-west-2
etcd_endpoints = zenith-1-etcd.local:2379

View File

@@ -1,38 +0,0 @@
---
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
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

@@ -1,8 +1,7 @@
#!/bin/sh
# fetch params from meta-data service
# get instance id 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=$(hostname -f)
@@ -13,20 +12,18 @@ cat <<EOF | tee /tmp/payload
"version": 1,
"host": "${HOST}",
"port": 6400,
"region_id": "{{ console_region_id }}",
"region_id": {{ console_region_id }},
"instance_id": "${INSTANCE_ID}",
"http_host": "${HOST}",
"http_port": 9898,
"active": false,
"availability_zone_id": "${AZ_ID}"
"http_port": 9898
}
EOF
# check if pageserver already registered or not
if ! curl -sf -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" {{ console_mgmt_base_url }}/management/api/v2/pageservers/${INSTANCE_ID} -o /dev/null; then
if ! curl -sf -X PATCH -d '{}' {{ console_mgmt_base_url }}/api/v1/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')
ID=$(curl -sf -X POST {{ console_mgmt_base_url }}/api/v1/pageservers -d@/tmp/payload | jq -r '.ID')
# init pageserver
sudo -u pageserver /usr/local/bin/pageserver -c "id=${ID}" -c "pg_distrib_dir='/usr/local'" --init -D /storage/pageserver/data

View File

@@ -14,18 +14,18 @@ cat <<EOF | tee /tmp/payload
"host": "${HOST}",
"port": 6500,
"http_port": 7676,
"region_id": "{{ console_region_id }}",
"region_id": {{ console_region_id }},
"instance_id": "${INSTANCE_ID}",
"availability_zone_id": "${AZ_ID}",
"active": false
"availability_zone_id": "${AZ_ID}"
}
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/${INSTANCE_ID} -o /dev/null; then
if ! curl -sf -X PATCH -d '{}' {{ console_mgmt_base_url }}/api/v1/safekeepers/${INSTANCE_ID} -o /dev/null; then
# not registered, so register it now
ID=$(curl -sf -X POST -H "Authorization: Bearer {{ CONSOLE_API_TOKEN }}" {{ console_mgmt_base_url }}/management/api/v2/safekeepers -d@/tmp/payload | jq -r '.id')
ID=$(curl -sf -X POST {{ console_mgmt_base_url }}/api/v1/safekeepers -d@/tmp/payload | jq -r '.ID')
# init safekeeper
sudo -u safekeeper /usr/local/bin/safekeeper --id ${ID} --init -D /storage/safekeeper/data
fi

View File

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

View File

@@ -1,36 +0,0 @@
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: development
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

20
.github/ansible/staging.hosts vendored Normal file
View File

@@ -0,0 +1,20 @@
[pageservers]
#zenith-us-stage-ps-1 console_region_id=27
zenith-us-stage-ps-2 console_region_id=27
zenith-us-stage-ps-3 console_region_id=27
[safekeepers]
zenith-us-stage-sk-4 console_region_id=27
zenith-us-stage-sk-5 console_region_id=27
zenith-us-stage-sk-6 console_region_id=27
[storage:children]
pageservers
safekeepers
[storage:vars]
env_name = us-stage
console_mgmt_base_url = http://console-staging.local
bucket_name = zenith-staging-storage-us-east-1
bucket_region = us-east-1
etcd_endpoints = zenith-us-stage-etcd.local:2379

View File

@@ -1,40 +0,0 @@
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: development
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
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

@@ -1,12 +1,12 @@
[Unit]
Description=Neon pageserver
Description=Zenith 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
Environment=RUST_BACKTRACE=1 NEON_REPO_DIR=/storage/pageserver LD_LIBRARY_PATH=/usr/local/lib
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_endpoints=['{{ etcd_endpoints }}']" -D /storage/pageserver/data
ExecReload=/bin/kill -HUP $MAINPID
KillMode=mixed
KillSignal=SIGINT

View File

@@ -1,12 +1,12 @@
[Unit]
Description=Neon safekeeper
Description=Zenith 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 }}"}'
Environment=RUST_BACKTRACE=1 NEON_REPO_DIR=/storage/safekeeper/data LD_LIBRARY_PATH=/usr/local/lib
ExecStart=/usr/local/bin/safekeeper -l {{ inventory_hostname }}.local:6500 --listen-http {{ inventory_hostname }}.local:7676 -D /storage/safekeeper/data --broker-endpoints={{ etcd_endpoints }} --remote-storage='{bucket_name="{{bucket_name}}", bucket_region="{{bucket_region}}", prefix_in_bucket="{{ env_name }}/wal"}'
ExecReload=/bin/kill -HUP $MAINPID
KillMode=mixed
KillSignal=SIGINT

View File

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

View File

@@ -1,57 +0,0 @@
# 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: "development"
# -- 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
#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

@@ -1,52 +0,0 @@
# 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: "development"

View File

@@ -1,65 +0,0 @@
# 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: "development"
# -- 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

@@ -1,57 +0,0 @@
# 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: "development"
# -- 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
#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

@@ -1,57 +0,0 @@
# 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: "development"
# -- 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
#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

@@ -1,52 +0,0 @@
# 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: "development"

View File

@@ -0,0 +1,26 @@
fullnameOverride: "neon-stress-proxy-scram"
settings:
authBackend: "console"
authEndpoint: "http://neon-stress-console.local/management/api/v2"
domain: "*.stress.neon.tech"
podLabels:
zenith_service: proxy-scram
zenith_env: staging
zenith_region: eu-west-1
zenith_region_slug: ireland
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: '*.stress.neon.tech'
metrics:
enabled: true
serviceMonitor:
enabled: true
selector:
release: kube-prometheus-stack

View File

@@ -0,0 +1,34 @@
fullnameOverride: "neon-stress-proxy"
settings:
authEndpoint: "https://console.dev.neon.tech/authenticate_proxy_request/"
uri: "https://console.dev.neon.tech/psql_session/"
# -- Additional labels for zenith-proxy pods
podLabels:
zenith_service: proxy
zenith_env: staging
zenith_region: eu-west-1
zenith_region_slug: ireland
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: neon-stress-proxy.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.dev.neon.tech
metrics:
enabled: true
serviceMonitor:
enabled: true
selector:
release: kube-prometheus-stack

View File

@@ -1,57 +0,0 @@
# 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"
# -- 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
#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

@@ -1,52 +0,0 @@
# 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

@@ -1,57 +0,0 @@
# 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"
# -- 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
#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

@@ -1,52 +0,0 @@
# 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

@@ -1,57 +0,0 @@
# 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"
# -- 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
#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

@@ -1,52 +0,0 @@
# 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

@@ -1,57 +0,0 @@
# 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"
# -- 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
#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

@@ -1,52 +0,0 @@
# 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

@@ -1,56 +0,0 @@
# 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

@@ -2,7 +2,6 @@ settings:
authBackend: "console"
authEndpoint: "http://console-release.local/management/api/v2"
domain: "*.cloud.neon.tech"
sentryEnvironment: "production"
podLabels:
zenith_service: proxy-scram
@@ -23,28 +22,3 @@ metrics:
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

@@ -1,8 +1,6 @@
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:
@@ -32,28 +30,3 @@ metrics:
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 +1,31 @@
# Helm chart values for zenith-proxy.
# 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"
# -- Additional labels for zenith-proxy pods
podLabels:
zenith_service: proxy-scram
zenith_env: staging
zenith_region: us-east-1
zenith_region_slug: virginia
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.stage.neon.tech
metrics:
enabled: true
serviceMonitor:
enabled: true
selector:
release: kube-prometheus-stack

30
.github/helm-values/staging.proxy.yaml vendored Normal file
View File

@@ -0,0 +1,30 @@
# Helm chart values for zenith-proxy.
# This is a YAML-formatted file.
image:
repository: neondatabase/neon
settings:
authEndpoint: "https://console.stage.neon.tech/authenticate_proxy_request/"
uri: "https://console.stage.neon.tech/psql_session/"
# -- Additional labels for zenith-proxy pods
podLabels:
zenith_service: proxy
zenith_env: staging
zenith_region: us-east-1
zenith_region_slug: virginia
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.stage.neon.tech
metrics:
enabled: true
serviceMonitor:
enabled: true
selector:
release: kube-prometheus-stack

View File

@@ -11,18 +11,9 @@ on:
# │ │ ┌───────────── day of the month (1 - 31)
# │ │ │ ┌───────────── month (1 - 12 or JAN-DEC)
# │ │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
- cron: '0 3 * * *' # run once a day, timezone is utc
- cron: '36 4 * * *' # run once a day, timezone is utc
workflow_dispatch: # adds ability to run this manually
inputs:
region_id:
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 or not. If not set, the report is published only for the main branch'
required: false
defaults:
run:
@@ -35,68 +26,94 @@ concurrency:
jobs:
bench:
env:
TEST_PG_BENCH_DURATIONS_MATRIX: "300"
TEST_PG_BENCH_SCALES_MATRIX: "10,100"
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
DEFAULT_PG_VERSION: 14
TEST_OUTPUT: /tmp/test_output
BUILD_TYPE: remote
SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref == 'refs/heads/main' ) }}
PLATFORM: "neon-staging"
# this workflow runs on self hosteed runner
# it's environment is quite different from usual guthub runner
# probably the most important difference is that it doesn't start from clean workspace each time
# e g if you install system packages they are not cleaned up since you install them directly in host machine
# not a container or something
# See documentation for more info: https://docs.github.com/en/actions/hosting-your-own-runners/about-self-hosted-runners
runs-on: [self-hosted, zenith-benchmarker]
runs-on: [ self-hosted, us-east-2, x64 ]
container:
image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
options: --init
env:
POSTGRES_DISTRIB_DIR: "/usr/pgsql-14"
steps:
- uses: actions/checkout@v3
- name: Checkout zenith repo
uses: actions/checkout@v3
- name: Download Neon artifact
uses: ./.github/actions/download
with:
name: neon-${{ runner.os }}-release-artifact
path: /tmp/neon/
prefix: latest
# actions/setup-python@v2 is not working correctly on self-hosted runners
# see https://github.com/actions/setup-python/issues/162
# and probably https://github.com/actions/setup-python/issues/162#issuecomment-865387976 in particular
# so the simplest solution to me is to use already installed system python and spin virtualenvs for job runs.
# there is Python 3.7.10 already installed on the machine so use it to install poetry and then use poetry's virtuealenvs
- name: Install poetry & deps
run: |
python3 -m pip install --upgrade poetry wheel
# since pip/poetry caches are reused there shouldn't be any troubles with install every time
./scripts/pysync
- name: Create Neon Project
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 }}
- name: Show versions
run: |
echo Python
python3 --version
poetry run python3 --version
echo Poetry
poetry --version
echo Pgbench
$POSTGRES_DISTRIB_DIR/bin/pgbench --version
# FIXME cluster setup is skipped due to various changes in console API
# for now pre created cluster is used. When API gain some stability
# after massive changes dynamic cluster setup will be revived.
# So use pre created cluster. It needs to be started manually, but stop is automatic after 5 minutes of inactivity
- name: Setup cluster
env:
BENCHMARK_CONNSTR: "${{ secrets.BENCHMARK_STAGING_CONNSTR }}"
run: |
set -e
echo "Starting cluster"
# wake up the cluster
$POSTGRES_DISTRIB_DIR/bin/psql $BENCHMARK_CONNSTR -c "SELECT 1"
- name: Run benchmark
uses: ./.github/actions/run-python-test-set
with:
build_type: ${{ env.BUILD_TYPE }}
test_selection: performance
run_in_parallel: false
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
# Set --sparse-ordering option of pytest-order plugin
# to ensure tests are running in order of appears in the file.
# It's important for test_perf_pgbench.py::test_pgbench_remote_* tests
extra_params: -m remote_cluster --sparse-ordering --timeout 5400 --ignore test_runner/performance/test_perf_olap.py
# pgbench is installed system wide from official repo
# https://download.postgresql.org/pub/repos/yum/13/redhat/rhel-7-x86_64/
# via
# sudo tee /etc/yum.repos.d/pgdg.repo<<EOF
# [pgdg13]
# name=PostgreSQL 13 for RHEL/CentOS 7 - x86_64
# baseurl=https://download.postgresql.org/pub/repos/yum/13/redhat/rhel-7-x86_64/
# enabled=1
# gpgcheck=0
# EOF
# sudo yum makecache
# sudo yum install postgresql13-contrib
# actual binaries are located in /usr/pgsql-13/bin/
env:
# The pgbench test runs two tests of given duration against each scale.
# So the total runtime with these parameters is 2 * 2 * 300 = 1200, or 20 minutes.
# Plus time needed to initialize the test databases.
TEST_PG_BENCH_DURATIONS_MATRIX: "300"
TEST_PG_BENCH_SCALES_MATRIX: "10,100"
PLATFORM: "neon-staging"
BENCHMARK_CONNSTR: "${{ secrets.BENCHMARK_STAGING_CONNSTR }}"
REMOTE_ENV: "1" # indicate to test harness that we do not have zenith binaries locally
run: |
# just to be sure that no data was cached on self hosted runner
# since it might generate duplicates when calling ingest_perf_test_result.py
rm -rf perf-report-staging
mkdir -p perf-report-staging
# Set --sparse-ordering option of pytest-order plugin to ensure tests are running in order of appears in the file,
# it's important for test_perf_pgbench.py::test_pgbench_remote_* tests
./scripts/pytest test_runner/performance/ -v -m "remote_cluster" --sparse-ordering --skip-interfering-proc-check --out-dir perf-report-staging --timeout 5400
- name: Submit result
env:
BENCHMARK_CONNSTR: ${{ steps.create-neon-project.outputs.dsn }}
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
- name: Delete Neon Project
if: ${{ always() }}
uses: ./.github/actions/neon-project-delete
with:
project_id: ${{ steps.create-neon-project.outputs.project_id }}
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
- name: Create Allure report
if: success() || failure()
uses: ./.github/actions/allure-report
with:
action: generate
build_type: ${{ env.BUILD_TYPE }}
run: |
REPORT_FROM=$(realpath perf-report-staging) REPORT_TO=staging scripts/generate_and_push_perf_report.sh
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
@@ -108,384 +125,104 @@ jobs:
SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
pgbench-compare:
strategy:
fail-fast: false
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"
TEST_PG_BENCH_SCALES_MATRIX: ${{ matrix.db_size }}
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
DEFAULT_PG_VERSION: 14
TEST_PG_BENCH_SCALES_MATRIX: "10gb"
REMOTE_ENV: "1"
POSTGRES_DISTRIB_DIR: /usr
TEST_OUTPUT: /tmp/test_output
BUILD_TYPE: remote
SAVE_PERF_REPORT: ${{ github.event.inputs.save_perf_report || ( github.ref == 'refs/heads/main' ) }}
PLATFORM: ${{ matrix.platform }}
runs-on: [ self-hosted, "${{ matrix.runner }}", x64 ]
container:
image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
options: --init
strategy:
fail-fast: false
matrix:
connstr: [ BENCHMARK_CAPTEST_CONNSTR, BENCHMARK_RDS_CONNSTR ]
runs-on: dev
container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rustlegacy:2817580636
timeout-minutes: 360 # 6h
steps:
- uses: actions/checkout@v3
- name: Download Neon artifact
uses: ./.github/actions/download
- name: Cache poetry deps
id: cache_poetry
uses: actions/cache@v3
with:
name: neon-${{ runner.os }}-release-artifact
path: /tmp/neon/
prefix: latest
path: ~/.cache/pypoetry/virtualenvs
key: v2-${{ runner.os }}-python-deps-${{ hashFiles('poetry.lock') }}
- name: Add Postgres binaries to PATH
run: |
${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin/pgbench --version
echo "${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin" >> $GITHUB_PATH
- name: Install Python deps
run: ./scripts/pysync
- name: Create Neon Project
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: ${{ secrets.NEON_STAGING_API_KEY }}
- name: Set up Connection String
id: set-up-connstr
run: |
case "${PLATFORM}" in
neon-captest-reuse)
CONNSTR=${{ secrets.BENCHMARK_CAPTEST_CONNSTR }}
;;
neon-captest-new | neon-captest-prefetch)
CONNSTR=${{ steps.create-neon-project.outputs.dsn }}
;;
rds-aurora)
CONNSTR=${{ secrets.BENCHMARK_RDS_AURORA_CONNSTR }}
;;
rds-postgres)
CONNSTR=${{ secrets.BENCHMARK_RDS_POSTGRES_CONNSTR }}
;;
*)
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
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"
- name: Calculate platform
id: calculate-platform
env:
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
CONNSTR: ${{ matrix.connstr }}
run: |
if [ "${CONNSTR}" = "BENCHMARK_CAPTEST_CONNSTR" ]; then
PLATFORM=neon-captest
elif [ "${CONNSTR}" = "BENCHMARK_RDS_CONNSTR" ]; then
PLATFORM=rds-aurora
else
echo 2>&1 "Unknown CONNSTR=${CONNSTR}. Allowed are BENCHMARK_CAPTEST_CONNSTR, and BENCHMARK_RDS_CONNSTR only"
exit 1
fi
echo "::set-output name=PLATFORM::${PLATFORM}"
- name: Install Deps
run: |
echo "deb http://apt.postgresql.org/pub/repos/apt focal-pgdg main" | sudo tee /etc/apt/sources.list.d/pgdg.list
wget --quiet -O - https://www.postgresql.org/media/keys/ACCC4CF8.asc | sudo apt-key add -
sudo apt -y update
sudo apt install -y postgresql-14 postgresql-client-14
- name: Benchmark init
uses: ./.github/actions/run-python-test-set
with:
build_type: ${{ env.BUILD_TYPE }}
test_selection: performance
run_in_parallel: false
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_init
env:
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
PLATFORM: ${{ steps.calculate-platform.outputs.PLATFORM }}
BENCHMARK_CONNSTR: ${{ secrets[matrix.connstr] }}
run: |
mkdir -p perf-report-captest
psql $BENCHMARK_CONNSTR -c "SELECT 1;"
./scripts/pytest test_runner/performance/test_perf_pgbench.py::test_pgbench_remote_init -v -m "remote_cluster" --skip-interfering-proc-check --out-dir perf-report-captest --timeout 21600
- name: Benchmark simple-update
uses: ./.github/actions/run-python-test-set
with:
build_type: ${{ env.BUILD_TYPE }}
test_selection: performance
run_in_parallel: false
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_simple_update
env:
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
PLATFORM: ${{ steps.calculate-platform.outputs.PLATFORM }}
BENCHMARK_CONNSTR: ${{ secrets[matrix.connstr] }}
run: |
psql $BENCHMARK_CONNSTR -c "SELECT 1;"
./scripts/pytest test_runner/performance/test_perf_pgbench.py::test_pgbench_remote_simple_update -v -m "remote_cluster" --skip-interfering-proc-check --out-dir perf-report-captest --timeout 21600
- name: Benchmark select-only
uses: ./.github/actions/run-python-test-set
with:
build_type: ${{ env.BUILD_TYPE }}
test_selection: performance
run_in_parallel: false
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_select_only
env:
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
PLATFORM: ${{ steps.calculate-platform.outputs.PLATFORM }}
BENCHMARK_CONNSTR: ${{ secrets[matrix.connstr] }}
run: |
psql $BENCHMARK_CONNSTR -c "SELECT 1;"
./scripts/pytest test_runner/performance/test_perf_pgbench.py::test_pgbench_remote_select_only -v -m "remote_cluster" --skip-interfering-proc-check --out-dir perf-report-captest --timeout 21600
- name: Submit result
env:
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
run: |
REPORT_FROM=$(realpath perf-report-captest) REPORT_TO=staging scripts/generate_and_push_perf_report.sh
- name: Delete Neon Project
if: ${{ steps.create-neon-project.outputs.project_id && always() }}
uses: ./.github/actions/neon-project-delete
- name: Upload logs
if: always()
uses: ./.github/actions/upload
with:
project_id: ${{ steps.create-neon-project.outputs.project_id }}
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
- name: Create Allure report
if: success() || failure()
uses: ./.github/actions/allure-report
with:
action: generate
build_type: ${{ env.BUILD_TYPE }}
name: bench-captest-${{ steps.calculate-platform.outputs.PLATFORM }}
path: /tmp/test_output/
- 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 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 }}
clickbench-compare:
# ClichBench DB for rds-aurora and rds-Postgres deployed to the same clusters
# we use for performance testing in pgbench-compare.
# Run this job only when pgbench-compare is finished to avoid the intersection.
# We might change it after https://github.com/neondatabase/neon/issues/2900.
#
# *_CLICKBENCH_CONNSTR: Genuine ClickBench DB with ~100M rows
# *_CLICKBENCH_10M_CONNSTR: DB with the first 10M rows of ClickBench DB
if: success() || failure()
needs: [ pgbench-compare ]
strategy:
fail-fast: false
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 == 'refs/heads/main' ) }}
PLATFORM: ${{ matrix.platform }}
runs-on: [ self-hosted, us-east-2, x64 ]
container:
image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
options: --init
timeout-minutes: 360 # 6h
steps:
- uses: actions/checkout@v3
- name: Download Neon artifact
uses: ./.github/actions/download
with:
name: neon-${{ runner.os }}-release-artifact
path: /tmp/neon/
prefix: latest
- name: Add Postgres binaries to PATH
run: |
${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin/pgbench --version
echo "${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin" >> $GITHUB_PATH
- name: Set up Connection String
id: set-up-connstr
run: |
case "${PLATFORM}" in
neon-captest-prefetch)
CONNSTR=${{ secrets.BENCHMARK_CAPTEST_CLICKBENCH_10M_CONNSTR }}
;;
rds-aurora)
CONNSTR=${{ secrets.BENCHMARK_RDS_AURORA_CLICKBENCH_10M_CONNSTR }}
;;
rds-postgres)
CONNSTR=${{ secrets.BENCHMARK_RDS_POSTGRES_CLICKBENCH_10M_CONNSTR }}
;;
*)
echo 2>&1 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-prefetch', 'rds-aurora', or 'rds-postgres'"
exit 1
;;
esac
echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
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
with:
build_type: ${{ env.BUILD_TYPE }}
test_selection: performance/test_perf_olap.py
run_in_parallel: false
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_clickbench
env:
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
- name: Create Allure report
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 OLAP 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 }}
tpch-compare:
# TCP-H DB for rds-aurora and rds-Postgres deployed to the same clusters
# we use for performance testing in pgbench-compare & clickbench-compare.
# Run this job only when clickbench-compare is finished to avoid the intersection.
# We might change it after https://github.com/neondatabase/neon/issues/2900.
#
# *_TPCH_S10_CONNSTR: DB generated with scale factor 10 (~10 GB)
if: success() || failure()
needs: [ clickbench-compare ]
strategy:
fail-fast: false
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 == 'refs/heads/main' ) }}
PLATFORM: ${{ matrix.platform }}
runs-on: [ self-hosted, us-east-2, x64 ]
container:
image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned
options: --init
timeout-minutes: 360 # 6h
steps:
- uses: actions/checkout@v3
- name: Download Neon artifact
uses: ./.github/actions/download
with:
name: neon-${{ runner.os }}-release-artifact
path: /tmp/neon/
prefix: latest
- name: Add Postgres binaries to PATH
run: |
${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin/pgbench --version
echo "${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/bin" >> $GITHUB_PATH
- name: Set up Connection String
id: set-up-connstr
run: |
case "${PLATFORM}" in
neon-captest-prefetch)
CONNSTR=${{ secrets.BENCHMARK_CAPTEST_TPCH_S10_CONNSTR }}
;;
rds-aurora)
CONNSTR=${{ secrets.BENCHMARK_RDS_AURORA_TPCH_S10_CONNSTR }}
;;
rds-postgres)
CONNSTR=${{ secrets.BENCHMARK_RDS_POSTGRES_TPCH_S10_CONNSTR }}
;;
*)
echo 2>&1 "Unknown PLATFORM=${PLATFORM}. Allowed only 'neon-captest-prefetch', 'rds-aurora', or 'rds-postgres'"
exit 1
;;
esac
echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
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
with:
build_type: ${{ env.BUILD_TYPE }}
test_selection: performance/test_perf_olap.py
run_in_parallel: false
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_tpch
env:
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
- name: Create Allure report
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 TPC-H perf testing ${{ matrix.platform }}: ${{ job.status }}\n${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}"
slack-message: "Periodic perf testing: ${{ job.status }}\n${{ 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

135
.github/workflows/codestyle.yml vendored Normal file
View File

@@ -0,0 +1,135 @@
name: Check code style and build
on:
push:
branches:
- main
pull_request:
defaults:
run:
shell: bash -euxo pipefail {0}
concurrency:
# Allow only one workflow per any non-`main` branch.
group: ${{ github.workflow }}-${{ github.ref }}-${{ github.ref == 'refs/heads/main' && github.sha || 'anysha' }}
cancel-in-progress: true
env:
RUST_BACKTRACE: 1
jobs:
check-codestyle-rust:
strategy:
fail-fast: false
matrix:
# If we want to duplicate this job for different
# Rust toolchains (e.g. nightly or 1.37.0), add them here.
rust_toolchain: [1.58]
os: [ubuntu-latest, macos-latest]
timeout-minutes: 60
name: run regression test suite
runs-on: ${{ matrix.os }}
steps:
- name: Checkout
uses: actions/checkout@v2
with:
submodules: true
fetch-depth: 2
- name: Install rust toolchain ${{ matrix.rust_toolchain }}
uses: actions-rs/toolchain@v1
with:
profile: minimal
toolchain: ${{ matrix.rust_toolchain }}
components: rustfmt, clippy
override: true
- name: Check formatting
run: cargo fmt --all -- --check
- name: Install Ubuntu postgres dependencies
if: matrix.os == 'ubuntu-latest'
run: |
sudo apt update
sudo apt install build-essential libreadline-dev zlib1g-dev flex bison libseccomp-dev libssl-dev
- name: Install macOS postgres dependencies
if: matrix.os == 'macos-latest'
run: brew install flex bison openssl
- name: Set pg revision for caching
id: pg_ver
run: echo ::set-output name=pg_rev::$(git rev-parse HEAD:vendor/postgres)
- name: Cache postgres build
id: cache_pg
uses: actions/cache@v2
with:
path: |
tmp_install/
key: ${{ runner.os }}-pg-${{ steps.pg_ver.outputs.pg_rev }}
- name: Set extra env for macOS
if: matrix.os == 'macos-latest'
run: |
echo 'LDFLAGS=-L/usr/local/opt/openssl@3/lib' >> $GITHUB_ENV
echo 'CPPFLAGS=-I/usr/local/opt/openssl@3/include' >> $GITHUB_ENV
- name: Build postgres
if: steps.cache_pg.outputs.cache-hit != 'true'
run: make postgres
# Plain configure output can contain weird errors like 'error: C compiler cannot create executables'
# and the real cause will be inside config.log
- name: Print configure logs in case of failure
if: failure()
continue-on-error: true
run: |
echo '' && echo '=== config.log ===' && echo ''
cat tmp_install/build/config.log
echo '' && echo '=== configure.log ===' && echo ''
cat tmp_install/build/configure.log
- name: Cache cargo deps
id: cache_cargo
uses: actions/cache@v2
with:
path: |
~/.cargo/registry
!~/.cargo/registry/src
~/.cargo/git
target
key: v2-${{ runner.os }}-cargo-${{ hashFiles('./Cargo.lock') }}-rust-${{ matrix.rust_toolchain }}
- name: Run cargo clippy
run: ./run_clippy.sh
- name: Ensure all project builds
run: cargo build --all --all-targets
check-codestyle-python:
runs-on: [ self-hosted, Linux, k8s-runner ]
steps:
- name: Checkout
uses: actions/checkout@v3
with:
submodules: false
fetch-depth: 1
- name: Cache poetry deps
id: cache_poetry
uses: actions/cache@v3
with:
path: ~/.cache/pypoetry/virtualenvs
key: v1-codestyle-python-deps-${{ hashFiles('poetry.lock') }}
- name: Install Python deps
run: ./scripts/pysync
- name: Run yapf to ensure code format
run: poetry run yapf --recursive --diff .
- name: Run mypy to check types
run: poetry run mypy .

View File

@@ -1,128 +0,0 @@
name: Check neon with extra platform builds
on:
push:
branches:
- main
defaults:
run:
shell: bash -euxo pipefail {0}
concurrency:
# Allow only one workflow per any non-`main` branch.
group: ${{ github.workflow }}-${{ github.ref }}-${{ github.ref == 'refs/heads/main' && github.sha || 'anysha' }}
cancel-in-progress: true
env:
RUST_BACKTRACE: 1
COPT: '-Werror'
jobs:
check-macos-build:
timeout-minutes: 90
runs-on: macos-latest
env:
# Use release build only, to have less debug info around
# Hence keeping target/ (and general cache size) smaller
BUILD_TYPE: release
steps:
- name: Checkout
uses: actions/checkout@v3
with:
submodules: true
fetch-depth: 1
- name: Install macOS postgres dependencies
run: brew install flex bison openssl protobuf
- name: Set pg 14 revision for caching
id: pg_v14_rev
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v14) >> $GITHUB_OUTPUT
- name: Set pg 15 revision for caching
id: pg_v15_rev
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v15) >> $GITHUB_OUTPUT
- name: Cache postgres v14 build
id: cache_pg_14
uses: actions/cache@v3
with:
path: pg_install/v14
key: v1-${{ 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 }}-${{ matrix.build_type }}-pg-${{ steps.pg_v15_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Set extra env for macOS
run: |
echo 'LDFLAGS=-L/usr/local/opt/openssl@3/lib' >> $GITHUB_ENV
echo 'CPPFLAGS=-I/usr/local/opt/openssl@3/include' >> $GITHUB_ENV
- name: Cache cargo deps
uses: actions/cache@v3
with:
path: |
~/.cargo/registry
!~/.cargo/registry/src
~/.cargo/git
target
key: v1-${{ runner.os }}-cargo-${{ hashFiles('./Cargo.lock') }}-${{ hashFiles('./rust-toolchain.toml') }}-rust
- name: Build postgres v14
if: steps.cache_pg_14.outputs.cache-hit != 'true'
run: make postgres-v14 -j$(nproc)
- name: Build postgres v15
if: steps.cache_pg_15.outputs.cache-hit != 'true'
run: make postgres-v15 -j$(nproc)
- name: Build neon extensions
run: make neon-pg-ext -j$(nproc)
- name: Run cargo build
run: cargo build --all --release
- name: Check that no warnings are produced
run: ./run_clippy.sh
gather-rust-build-stats:
timeout-minutes: 90
runs-on: ubuntu-latest
env:
BUILD_TYPE: release
# build with incremental compilation produce partial results
# so do not attempt to cache this build, also disable the incremental compilation
CARGO_INCREMENTAL: 0
steps:
- name: Checkout
uses: actions/checkout@v3
with:
submodules: true
fetch-depth: 1
- name: Install Ubuntu postgres dependencies
run: |
sudo apt update
sudo apt install build-essential libreadline-dev zlib1g-dev flex bison libseccomp-dev libssl-dev protobuf-compiler
# Some of our rust modules use FFI and need those to be checked
- name: Get postgres headers
run: make postgres-headers -j$(nproc)
- name: Produce the build stats
run: cargo build --all --release --timings
- name: Upload the build stats
uses: actions/upload-artifact@v3
with:
name: neon-${{ runner.os }}-release-build-stats
path: ./target/cargo-timings/

45
.github/workflows/notifications.yml vendored Normal file
View File

@@ -0,0 +1,45 @@
name: Send Notifications
on:
push:
branches: [ main ]
jobs:
send-notifications:
timeout-minutes: 30
name: send commit notifications
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@v2
with:
submodules: true
fetch-depth: 2
- name: Form variables for notification message
id: git_info_grab
run: |
git_stat=$(git show --stat=50)
git_stat="${git_stat//'%'/'%25'}"
git_stat="${git_stat//$'\n'/'%0A'}"
git_stat="${git_stat//$'\r'/'%0D'}"
git_stat="${git_stat// /}" # space -> 'Space En', as github tends to eat ordinary spaces
echo "::set-output name=git_stat::$git_stat"
echo "::set-output name=sha_short::$(git rev-parse --short HEAD)"
echo "##[set-output name=git_branch;]$(echo ${GITHUB_REF#refs/heads/})"
- name: Send notification
uses: appleboy/telegram-action@master
with:
to: ${{ secrets.TELEGRAM_TO }}
token: ${{ secrets.TELEGRAM_TOKEN }}
format: markdown
args: |
*@${{ github.actor }} pushed to* [${{ github.repository }}:${{steps.git_info_grab.outputs.git_branch}}](github.com/${{ github.repository }}/commit/${{steps.git_info_grab.outputs.sha_short }})
```
${{ steps.git_info_grab.outputs.git_stat }}
```

View File

@@ -23,7 +23,6 @@ jobs:
runs-on: [ ubuntu-latest ]
env:
DEFAULT_PG_VERSION: 14
TEST_OUTPUT: /tmp/test_output
steps:
@@ -48,23 +47,17 @@ jobs:
shell: bash -euxo pipefail {0}
run: ./scripts/pysync
- name: Create Neon Project
id: create-neon-project
uses: ./.github/actions/neon-project-create
with:
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
postgres_version: ${{ env.DEFAULT_PG_VERSION }}
- name: Run pytest
env:
REMOTE_ENV: 1
BENCHMARK_CONNSTR: ${{ steps.create-neon-project.outputs.dsn }}
BENCHMARK_CONNSTR: "${{ secrets.BENCHMARK_STAGING_CONNSTR }}"
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
shell: bash -euxo pipefail {0}
run: |
# Test framework expects we have psql binary;
# but since we don't really need it in this test, let's mock it
mkdir -p "$POSTGRES_DISTRIB_DIR/v${DEFAULT_PG_VERSION}/bin" && touch "$POSTGRES_DISTRIB_DIR/v${DEFAULT_PG_VERSION}/bin/psql";
mkdir -p "$POSTGRES_DISTRIB_DIR/bin" && touch "$POSTGRES_DISTRIB_DIR/bin/psql";
./scripts/pytest \
--junitxml=$TEST_OUTPUT/junit.xml \
--tb=short \
@@ -72,13 +65,6 @@ jobs:
-m "remote_cluster" \
-rA "test_runner/pg_clients"
- name: Delete Neon Project
if: ${{ always() }}
uses: ./.github/actions/neon-project-delete
with:
project_id: ${{ steps.create-neon-project.outputs.project_id }}
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
# We use GitHub's action upload-artifact because `ubuntu-latest` doesn't have configured AWS CLI.
# It will be fixed after switching to gen2 runner
- name: Upload python test logs

6
.gitignore vendored
View File

@@ -1,6 +1,7 @@
/pg_install
/target
/bindings/python/neon-dev-utils/target
/tmp_check
/tmp_install
/tmp_check_cli
__pycache__/
test_output/
@@ -15,6 +16,3 @@ test_output/
*.key
*.crt
*.o
*.so
*.Po

12
.gitmodules vendored
View File

@@ -1,8 +1,4 @@
[submodule "vendor/postgres-v14"]
path = vendor/postgres-v14
url = https://github.com/neondatabase/postgres.git
branch = REL_14_STABLE_neon
[submodule "vendor/postgres-v15"]
path = vendor/postgres-v15
url = https://github.com/neondatabase/postgres.git
branch = REL_15_STABLE_neon
[submodule "vendor/postgres"]
path = vendor/postgres
url = https://github.com/zenithdb/postgres
branch = main

10
.yapfignore Normal file
View File

@@ -0,0 +1,10 @@
# This file is only read when `yapf` is run from this directory.
# Hence we only top-level directories here to avoid confusion.
# See source code for the exact file format: https://github.com/google/yapf/blob/c6077954245bc3add82dafd853a1c7305a6ebd20/yapf/yapflib/file_resources.py#L40-L43
vendor/
target/
tmp_install/
__pycache__/
test_output/
.neon/
.git/

View File

@@ -1,11 +0,0 @@
/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
/pageserver/ @neondatabase/compute @neondatabase/storage
/pgxn/ @neondatabase/compute
/proxy/ @neondatabase/control-plane
/safekeeper/ @neondatabase/safekeepers
/vendor/ @neondatabase/compute

2633
Cargo.lock generated

File diff suppressed because it is too large Load Diff

View File

@@ -1,14 +1,3 @@
# 'named-profiles' feature was stabilized in cargo 1.57. This line makes the
# build work with older cargo versions.
#
# We have this because as of this writing, the latest cargo Debian package
# that's available is 1.56. (Confusingly, the Debian package version number
# is 0.57, whereas 'cargo --version' says 1.56.)
#
# See https://tracker.debian.org/pkg/cargo for the current status of the
# package. When that gets updated, we can remove this.
cargo-features = ["named-profiles"]
[workspace]
members = [
"compute_tools",
@@ -16,74 +5,22 @@ members = [
"pageserver",
"proxy",
"safekeeper",
"storage_broker",
"workspace_hack",
"neon_local",
"integration_tests",
"libs/*",
]
exclude = [
"bindings/python/neon-dev-utils",
]
[profile.release]
# This is useful for profiling and, to some extent, debug.
# Besides, debug info should not affect the performance.
debug = true
# disable debug symbols for all packages except this one to decrease binaries size
[profile.release.package."*"]
debug = false
[profile.release-line-debug]
inherits = "release"
debug = 1 # true = 2 = all symbols, 1 = line only
[profile.release-line-debug-lto]
inherits = "release"
debug = 1 # true = 2 = all symbols, 1 = line only
lto = true
[profile.release-line-debug-size]
inherits = "release"
debug = 1 # true = 2 = all symbols, 1 = line only
opt-level = "s"
[profile.release-line-debug-zize]
inherits = "release"
debug = 1 # true = 2 = all symbols, 1 = line only
opt-level = "z"
[profile.release-line-debug-size-lto]
inherits = "release"
debug = 1 # true = 2 = all symbols, 1 = line only
opt-level = "s"
lto = true
[profile.release-line-debug-zize-lto]
inherits = "release"
debug = 1 # true = 2 = all symbols, 1 = line only
opt-level = "z"
lto = true
[profile.release-no-debug]
inherits = "release"
debug = false # true = 2 = all symbols, 1 = line only
[profile.release-no-debug-size]
inherits = "release"
debug = false # true = 2 = all symbols, 1 = line only
opt-level = "s"
[profile.release-no-debug-zize]
inherits = "release"
debug = false # true = 2 = all symbols, 1 = line only
opt-level = "z"
[profile.release-no-debug-size-lto]
inherits = "release"
debug = false # true = 2 = all symbols, 1 = line only
opt-level = "s"
lto = true
[profile.release-no-debug-zize-lto]
inherits = "release"
debug = false # true = 2 = all symbols, 1 = line only
opt-level = "z"
lto = true
# This is only needed for proxy's tests.
# TODO: we should probably fork `tokio-postgres-rustls` instead.
[patch.crates-io]
tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e" }
tokio-postgres = { git = "https://github.com/zenithdb/rust-postgres.git", rev="d052ee8b86fff9897c77b0fe89ea9daba0e1fa38" }

View File

@@ -1,29 +1,18 @@
### Creates a storage Docker image with postgres, pageserver, safekeeper and proxy binaries.
### 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=369495373322.dkr.ecr.eu-central-1.amazonaws.com
ARG IMAGE=rust
ARG TAG=pinned
# Build Postgres
FROM $REPOSITORY/$IMAGE:$TAG AS pg-build
FROM 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned AS pg-build
WORKDIR /home/nonroot
COPY --chown=nonroot vendor/postgres-v14 vendor/postgres-v14
COPY --chown=nonroot vendor/postgres-v15 vendor/postgres-v15
COPY --chown=nonroot pgxn pgxn
COPY --chown=nonroot Makefile Makefile
COPY --chown=nonroot scripts/ninstall.sh scripts/ninstall.sh
COPY vendor/postgres vendor/postgres
COPY Makefile Makefile
ENV BUILD_TYPE release
RUN set -e \
&& mold -run make -j $(nproc) -s neon-pg-ext \
&& rm -rf pg_install/build \
&& tar -C pg_install -czf /home/nonroot/postgres_install.tar.gz .
&& mold -run make -j $(nproc) -s postgres \
&& rm -rf tmp_install/build \
&& tar -C tmp_install -czf /home/nonroot/postgres_install.tar.gz .
# Build neon binaries
FROM $REPOSITORY/$IMAGE:$TAG AS build
# Build zenith binaries
FROM 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned AS build
WORKDIR /home/nonroot
ARG GIT_VERSION=local
@@ -37,14 +26,13 @@ ARG CACHEPOT_BUCKET=neon-github-dev
#ARG AWS_ACCESS_KEY_ID
#ARG AWS_SECRET_ACCESS_KEY
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/tmp_install/include/postgresql/server tmp_install/include/postgresql/server
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 pageserver --bin pageserver_binutils --bin draw_timeline_dir --bin safekeeper --bin storage_broker --bin proxy --locked --release \
&& mold -run cargo build --release \
&& cachepot -s
# Build final image
@@ -60,31 +48,17 @@ RUN set -e \
openssl \
ca-certificates \
&& rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* \
&& useradd -d /data neon \
&& chown -R neon:neon /data
&& useradd -d /data zenith \
&& chown -R zenith:zenith /data
COPY --from=build --chown=neon:neon /home/nonroot/target/release/pageserver /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=zenith:zenith /home/nonroot/target/release/pageserver /usr/local/bin
COPY --from=build --chown=zenith:zenith /home/nonroot/target/release/safekeeper /usr/local/bin
COPY --from=build --chown=zenith:zenith /home/nonroot/target/release/proxy /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/tmp_install/ /usr/local/
COPY --from=pg-build /home/nonroot/postgres_install.tar.gz /data/
# By default, pageserver uses `.neon/` working directory in WORKDIR, so create one and fill it with the dummy config.
# Now, when `docker run ... pageserver` is run, it can start without errors, yet will have some default dummy values.
RUN mkdir -p /data/.neon/ && chown -R neon:neon /data/.neon/ \
&& /usr/local/bin/pageserver -D /data/.neon/ --init \
-c "id=1234" \
-c "broker_endpoint='http://storage_broker:50051'" \
-c "pg_distrib_dir='/usr/local/'" \
-c "listen_pg_addr='0.0.0.0:6400'" \
-c "listen_http_addr='0.0.0.0:9898'"
VOLUME ["/data"]
USER neon
USER zenith
EXPOSE 6400
EXPOSE 9898
CMD ["pageserver"]

View File

@@ -1,212 +0,0 @@
#
# 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 $(getconf _NPROCESSORS_ONLN) -s -C src/interfaces/libpq install
#########################################################################################
#
# Layer "postgis-build"
# Build PostGIS from the upstream PostGIS mirror.
#
#########################################################################################
FROM build-deps AS postgis-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN apt update && \
apt install -y gdal-bin libgdal-dev libprotobuf-c-dev protobuf-c-compiler xsltproc
RUN wget https://download.osgeo.org/postgis/source/postgis-3.3.1.tar.gz && \
tar xvzf postgis-3.3.1.tar.gz && \
cd postgis-3.3.1 && \
./autogen.sh && \
export PATH="/usr/local/pgsql/bin:$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
#########################################################################################
#
# 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

@@ -1,212 +0,0 @@
#
# 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 $(getconf _NPROCESSORS_ONLN) -s -C src/interfaces/libpq install
#########################################################################################
#
# Layer "postgis-build"
# Build PostGIS from the upstream PostGIS mirror.
#
#########################################################################################
FROM build-deps AS postgis-build
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
RUN apt update && \
apt install -y gdal-bin libgdal-dev libprotobuf-c-dev protobuf-c-compiler xsltproc
RUN wget https://download.osgeo.org/postgis/source/postgis-3.3.1.tar.gz && \
tar xvzf postgis-3.3.1.tar.gz && \
cd postgis-3.3.1 && \
./autogen.sh && \
export PATH="/usr/local/pgsql/bin:$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
#########################################################################################
#
# 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

@@ -1,10 +1,6 @@
# 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=369495373322.dkr.ecr.eu-central-1.amazonaws.com
ARG IMAGE=rust
ARG TAG=pinned
FROM $REPOSITORY/$IMAGE:$TAG AS rust-build
FROM 369495373322.dkr.ecr.eu-central-1.amazonaws.com/rust:pinned AS rust-build
WORKDIR /home/nonroot
# Enable https://github.com/paritytech/cachepot to cache Rust crates' compilation results in Docker builds.
@@ -20,7 +16,7 @@ ARG CACHEPOT_BUCKET=neon-github-dev
COPY . .
RUN set -e \
&& mold -run cargo build -p compute_tools --locked --release \
&& mold -run cargo build -p compute_tools --release \
&& cachepot -s
# Final image that only has one binary

174
Makefile
View File

@@ -1,7 +1,15 @@
ROOT_PROJECT_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
# Where to install Postgres, default is ./pg_install, maybe useful for package managers
POSTGRES_INSTALL_DIR ?= $(ROOT_PROJECT_DIR)/pg_install/
# Where to install Postgres, default is ./tmp_install, maybe useful for package managers
POSTGRES_INSTALL_DIR ?= $(ROOT_PROJECT_DIR)/tmp_install
# Seccomp BPF is only available for Linux
UNAME_S := $(shell uname -s)
ifeq ($(UNAME_S),Linux)
SECCOMP = --with-libseccomp
else
SECCOMP =
endif
#
# We differentiate between release / debug build types using the BUILD_TYPE
@@ -20,26 +28,14 @@ else
$(error Bad build type '$(BUILD_TYPE)', see Makefile for options)
endif
# macOS with brew-installed openssl requires explicit paths
# It can be configured with OPENSSL_PREFIX variable
UNAME_S := $(shell uname -s)
ifeq ($(UNAME_S),Linux)
# Seccomp BPF is only available for Linux
PG_CONFIGURE_OPTS += --with-libseccomp
else ifeq ($(UNAME_S),Darwin)
# macOS with brew-installed openssl requires explicit paths
# 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
# 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/:
ifeq ($(UNAME_S),Darwin)
OPENSSL_PREFIX ?= $(shell brew --prefix openssl@3)
PG_CONFIGURE_OPTS += --with-includes=$(OPENSSL_PREFIX)/include --with-libraries=$(OPENSSL_PREFIX)/lib
endif
# Use -C option so that when PostgreSQL "make install" installs the
# headers, the mtime of the headers are not changed when there have
# been no changes to the files. Changing the mtime triggers an
# unnecessary rebuild of 'postgres_ffi'.
PG_CONFIGURE_OPTS += INSTALL='$(ROOT_PROJECT_DIR)/scripts/ninstall.sh -C'
# Choose whether we should be silent or verbose
CARGO_BUILD_FLAGS += --$(if $(filter s,$(MAKEFLAGS)),quiet,verbose)
# Fix for a corner case when make doesn't pass a jobserver
@@ -52,123 +48,63 @@ CARGO_CMD_PREFIX += $(if $(filter n,$(MAKEFLAGS)),,+)
CARGO_CMD_PREFIX += CARGO_TERM_PROGRESS_WHEN=never CI=1
#
# Top level Makefile to build Neon and PostgreSQL
# Top level Makefile to build Zenith and PostgreSQL
#
.PHONY: all
all: neon postgres neon-pg-ext
all: zenith postgres
### Neon Rust bits
### Zenith Rust bits
#
# The 'postgres_ffi' depends on the Postgres headers.
.PHONY: neon
neon: postgres-headers
+@echo "Compiling Neon"
.PHONY: zenith
zenith: postgres-headers
+@echo "Compiling Zenith"
$(CARGO_CMD_PREFIX) cargo build $(CARGO_BUILD_FLAGS)
### PostgreSQL parts
# Some rules are duplicated for Postgres v14 and 15. We may want to refactor
# to avoid the duplication in the future, but it's tolerable for now.
#
$(POSTGRES_INSTALL_DIR)/build/%/config.status:
+@echo "Configuring Postgres $* build"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/$*
(cd $(POSTGRES_INSTALL_DIR)/build/$* && \
env PATH="$(EXTRA_PATH_OVERRIDES):$$PATH" $(ROOT_PROJECT_DIR)/vendor/postgres-$*/configure \
CFLAGS='$(PG_CFLAGS)' \
$(POSTGRES_INSTALL_DIR)/build/config.status:
+@echo "Configuring postgres build"
mkdir -p $(POSTGRES_INSTALL_DIR)/build
(cd $(POSTGRES_INSTALL_DIR)/build && \
$(ROOT_PROJECT_DIR)/vendor/postgres/configure CFLAGS='$(PG_CFLAGS)' \
$(PG_CONFIGURE_OPTS) \
--prefix=$(abspath $(POSTGRES_INSTALL_DIR))/$* > configure.log)
$(SECCOMP) \
--prefix=$(abspath $(POSTGRES_INSTALL_DIR)) > configure.log)
# nicer alias to run 'configure'
# Note: I've been unable to use templates for this part of our configuration.
# I'm not sure why it wouldn't work, but this is the only place (apart from
# the "build-all-versions" entry points) where direct mention of PostgreSQL
# versions is used.
.PHONY: postgres-configure-v15
postgres-configure-v15: $(POSTGRES_INSTALL_DIR)/build/v15/config.status
.PHONY: postgres-configure-v14
postgres-configure-v14: $(POSTGRES_INSTALL_DIR)/build/v14/config.status
# Install the PostgreSQL header files into $(POSTGRES_INSTALL_DIR)/<version>/include
.PHONY: postgres-headers-%
postgres-headers-%: postgres-configure-%
+@echo "Installing PostgreSQL $* headers"
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/src/include MAKELEVEL=0 install
# Compile and install PostgreSQL
.PHONY: postgres-%
postgres-%: postgres-configure-% \
postgres-headers-% # to prevent `make install` conflicts with neon's `postgres-headers`
+@echo "Compiling PostgreSQL $*"
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$* MAKELEVEL=0 install
+@echo "Compiling libpq $*"
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/src/interfaces/libpq install
+@echo "Compiling pg_prewarm $*"
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pg_prewarm install
+@echo "Compiling pg_buffercache $*"
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pg_buffercache install
+@echo "Compiling pageinspect $*"
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pageinspect install
.PHONY: postgres-clean-%
postgres-clean-%:
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$* MAKELEVEL=0 clean
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pg_buffercache clean
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pageinspect clean
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/src/interfaces/libpq clean
.PHONY: neon-pg-ext-%
neon-pg-ext-%: postgres-%
+@echo "Compiling neon $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile install
+@echo "Compiling neon_walredo $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-walredo-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-walredo-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_walredo/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
.PHONY: neon-pg-ext-clean-%
neon-pg-ext-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
.PHONY: neon-pg-ext-clean
neon-pg-ext-clean: \
neon-pg-ext-clean-v14 \
neon-pg-ext-clean-v15
# shorthand to build all Postgres versions
.PHONY: postgres
postgres: \
postgres-v14 \
postgres-v15
# nicer alias for running 'configure'
.PHONY: postgres-configure
postgres-configure: $(POSTGRES_INSTALL_DIR)/build/config.status
# Install the PostgreSQL header files into $(POSTGRES_INSTALL_DIR)/include
.PHONY: postgres-headers
postgres-headers: \
postgres-headers-v14 \
postgres-headers-v15
postgres-headers: postgres-configure
+@echo "Installing PostgreSQL headers"
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/src/include MAKELEVEL=0 install
# Compile and install PostgreSQL and contrib/neon
.PHONY: postgres
postgres: postgres-configure \
postgres-headers # to prevent `make install` conflicts with zenith's `postgres-headers`
+@echo "Compiling PostgreSQL"
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build MAKELEVEL=0 install
+@echo "Compiling contrib/neon"
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/contrib/neon install
+@echo "Compiling contrib/neon_test_utils"
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/contrib/neon_test_utils install
+@echo "Compiling pg_buffercache"
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/contrib/pg_buffercache install
+@echo "Compiling pageinspect"
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/contrib/pageinspect install
.PHONY: postgres-clean
postgres-clean: \
postgres-clean-v14 \
postgres-clean-v15
postgres-clean:
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build MAKELEVEL=0 clean
# This doesn't remove the effects of 'configure'.
.PHONY: clean
clean: postgres-clean neon-pg-ext-clean
clean:
cd $(POSTGRES_INSTALL_DIR)/build && $(MAKE) clean
$(CARGO_CMD_PREFIX) cargo clean
# This removes everything

4
NOTICE
View File

@@ -1,5 +1,5 @@
Neon
Copyright 2022 Neon Inc.
The PostgreSQL submodules in vendor/postgres-v14 and vendor/postgres-v15 are licensed under the
PostgreSQL license. See vendor/postgres-v14/COPYRIGHT and vendor/postgres-v15/COPYRIGHT.
The PostgreSQL submodule in vendor/postgres is licensed under the
PostgreSQL license. See vendor/postgres/COPYRIGHT.

View File

@@ -2,21 +2,29 @@
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.
The project used to be called "Zenith". Many of the commands and code comments
still refer to "zenith", but we are in the process of renaming things.
## Quick start
Try the [Neon Free Tier](https://neon.tech/docs/introduction/technical-preview-free-tier/) to create a serverless Postgres instance. Then connect to it with your preferred Postgres client (psql, dbeaver, etc) or use the online [SQL Editor](https://neon.tech/docs/get-started-with-neon/query-with-neon-sql-editor/). See [Connect from any application](https://neon.tech/docs/connect/connect-from-any-app/) for connection instructions.
[Join the waitlist](https://neon.tech/) for our free tier to receive your serverless postgres instance. Then connect to it with your preferred postgres client (psql, dbeaver, etc) or use the online SQL editor.
Alternatively, compile and run the project [locally](#running-local-installation).
## Architecture overview
A Neon installation consists of compute nodes and the Neon storage engine. Compute nodes are stateless PostgreSQL nodes backed by the Neon storage engine.
A Neon installation consists of compute nodes and a Neon storage engine.
Compute nodes are stateless PostgreSQL nodes backed by the Neon storage engine.
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 [/docs/SUMMARY.md](/docs/SUMMARY.md) for more information.
- WAL service. The service receives WAL from the compute node and ensures that it is stored durably.
Pageserver consists of:
- Repository - Neon storage implementation.
- WAL receiver - service that receives WAL from WAL service and stores it in the repository.
- Page service - service that communicates with compute nodes and responds with pages from the repository.
- WAL redo - service that builds pages from base images and WAL records on Page service request
## Running local installation
@@ -26,13 +34,12 @@ See developer documentation in [/docs/SUMMARY.md](/docs/SUMMARY.md) for more inf
* 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
libssl-dev clang pkg-config libpq-dev etcd cmake postgresql-client
```
* 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
libseccomp-devel perl clang cmake etcd postgresql postgresql-contrib
```
2. [Install Rust](https://www.rust-lang.org/tools/install)
@@ -45,7 +52,7 @@ curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
1. Install XCode and dependencies
```
xcode-select --install
brew install protobuf openssl flex bison
brew install protobuf etcd openssl
```
2. [Install Rust](https://www.rust-lang.org/tools/install)
@@ -61,17 +68,6 @@ brew install libpq
brew link --force libpq
```
#### Rustc version
The project uses [rust toolchain file](./rust-toolchain.toml) to define the version it's built with in CI for testing and local builds.
This file is automatically picked up by [`rustup`](https://rust-lang.github.io/rustup/overrides.html#the-toolchain-file) that installs (if absent) and uses the toolchain version pinned in the file.
rustup users who want to build with another toolchain can use [`rustup override`](https://rust-lang.github.io/rustup/overrides.html#directory-overrides) command to set a specific toolchain for the project's directory.
non-rustup users most probably are not getting the same toolchain automatically from the file, so are responsible to manually verify their toolchain matches the version in the file.
Newer rustc versions most probably will work fine, yet older ones might not be supported due to some new features used by the project or the crates.
#### Building on Linux
1. Build neon and patched postgres
@@ -81,9 +77,9 @@ Newer rustc versions most probably will work fine, yet older ones might not be s
git clone --recursive https://github.com/neondatabase/neon.git
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`"
# The preferred and default is to make a debug build. This will create a
# demonstrably slower build than a release build. If you want to use a release
# build, utilize "BUILD_TYPE=release make -j`nproc`"
make -j`nproc`
```
@@ -97,15 +93,15 @@ make -j`nproc`
git clone --recursive https://github.com/neondatabase/neon.git
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`"
# The preferred and default is to make a debug build. This will create a
# demonstrably slower build than a release build. If you want to use a release
# build, utilize "BUILD_TYPE=release make -j`sysctl -n hw.logicalcpu`"
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 `psql` client, install the `postgresql-client` package or modify `PATH` and `LD_LIBRARY_PATH` to include `tmp_install/bin` and `tmp_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](https://python-poetry.org/)) in the project directory.
@@ -117,23 +113,22 @@ Python (3.9 or higher), and install python3 packages using `./scripts/pysync` (r
# Create repository in .neon with proper paths to binaries and data
# Later that would be responsibility of a package install script
> ./target/debug/neon_local init
Starting pageserver at '127.0.0.1:64000' in '.neon'.
pageserver started, pid: 2545906
Successfully initialized timeline de200bd42b49cc1814412c7e592dd6e9
Stopped pageserver 1 process with pid 2545906
initializing tenantid 9ef87a5bf0d92544f6fafeeb3239695c
created initial timeline de200bd42b49cc1814412c7e592dd6e9 timeline.lsn 0/16B5A50
initial timeline de200bd42b49cc1814412c7e592dd6e9 created
pageserver init succeeded
# start pageserver and safekeeper
> ./target/debug/neon_local start
Starting neon broker at 127.0.0.1:50051
storage_broker started, pid: 2918372
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
Starting pageserver at '127.0.0.1:64000' in '.neon'
Pageserver started
initializing for sk 1 for 7676
Starting safekeeper at '127.0.0.1:5454' in '.neon/safekeepers/sk1'
Safekeeper started
# start postgres compute node
> ./target/debug/neon_local pg start main
Starting new postgres (v14) main on timeline de200bd42b49cc1814412c7e592dd6e9 ...
Starting new postgres 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'
@@ -213,28 +208,18 @@ Ensure your dependencies are installed as described [here](https://github.com/ne
```sh
git clone --recursive https://github.com/neondatabase/neon.git
CARGO_BUILD_FLAGS="--features=testing" make
make # builds also postgres and installs it to ./tmp_install
./scripts/pytest
```
## Documentation
[/docs/](/docs/) Contains a top-level overview of all available markdown documentation.
Now we use README files to cover design ideas and overall architecture for each module and `rustdoc` style documentation comments. See also [/docs/](/docs/) a top-level overview of all available markdown documentation.
- [/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`
See also README files in some source directories, and `rustdoc` style documentation comments.
Other resources:
- [SELECT 'Hello, World'](https://neon.tech/blog/hello-world/): Blog post by Nikita Shamgunov on the high level architecture
- [Architecture decisions in Neon](https://neon.tech/blog/architecture-decisions-in-neon/): Blog post by Heikki Linnakangas
- [Neon: Serverless PostgreSQL!](https://www.youtube.com/watch?v=rES0yzeERns): Presentation on storage system by Heikki Linnakangas in the CMU Database Group seminar series
### Postgres-specific terms
Due to Neon's very close relation with PostgreSQL internals, numerous specific terms are used.

264
bindings/python/neon-dev-utils/Cargo.lock generated Normal file
View File

@@ -0,0 +1,264 @@
# This file is automatically @generated by Cargo.
# It is not intended for manual editing.
version = 3
[[package]]
name = "autocfg"
version = "1.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d468802bab17cbc0cc575e9b053f41e72aa36bfa6b7f55e3529ffa43161b97fa"
[[package]]
name = "bitflags"
version = "1.3.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"
[[package]]
name = "cfg-if"
version = "1.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
[[package]]
name = "indoc"
version = "0.3.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "47741a8bc60fb26eb8d6e0238bbb26d8575ff623fdc97b1a2c00c050b9684ed8"
dependencies = [
"indoc-impl",
"proc-macro-hack",
]
[[package]]
name = "indoc-impl"
version = "0.3.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ce046d161f000fffde5f432a0d034d0341dc152643b2598ed5bfce44c4f3a8f0"
dependencies = [
"proc-macro-hack",
"proc-macro2",
"quote",
"syn",
"unindent",
]
[[package]]
name = "instant"
version = "0.1.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7a5bbe824c507c5da5956355e86a746d82e0e1464f65d862cc5e71da70e94b2c"
dependencies = [
"cfg-if",
]
[[package]]
name = "libc"
version = "0.2.132"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8371e4e5341c3a96db127eb2465ac681ced4c433e01dd0e938adbef26ba93ba5"
[[package]]
name = "lock_api"
version = "0.4.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9f80bf5aacaf25cbfc8210d1cfb718f2bf3b11c4c54e5afe36c236853a8ec390"
dependencies = [
"autocfg",
"scopeguard",
]
[[package]]
name = "neon-dev-utils"
version = "0.1.0"
dependencies = [
"pyo3",
]
[[package]]
name = "once_cell"
version = "1.13.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "074864da206b4973b84eb91683020dbefd6a8c3f0f38e054d93954e891935e4e"
[[package]]
name = "parking_lot"
version = "0.11.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7d17b78036a60663b797adeaee46f5c9dfebb86948d1255007a1d6be0271ff99"
dependencies = [
"instant",
"lock_api",
"parking_lot_core",
]
[[package]]
name = "parking_lot_core"
version = "0.8.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d76e8e1493bcac0d2766c42737f34458f1c8c50c0d23bcb24ea953affb273216"
dependencies = [
"cfg-if",
"instant",
"libc",
"redox_syscall",
"smallvec",
"winapi",
]
[[package]]
name = "paste"
version = "0.1.18"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "45ca20c77d80be666aef2b45486da86238fabe33e38306bd3118fe4af33fa880"
dependencies = [
"paste-impl",
"proc-macro-hack",
]
[[package]]
name = "paste-impl"
version = "0.1.18"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d95a7db200b97ef370c8e6de0088252f7e0dfff7d047a28528e47456c0fc98b6"
dependencies = [
"proc-macro-hack",
]
[[package]]
name = "proc-macro-hack"
version = "0.5.19"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "dbf0c48bc1d91375ae5c3cd81e3722dff1abcf81a30960240640d223f59fe0e5"
[[package]]
name = "proc-macro2"
version = "1.0.43"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0a2ca2c61bc9f3d74d2886294ab7b9853abd9c1ad903a3ac7815c58989bb7bab"
dependencies = [
"unicode-ident",
]
[[package]]
name = "pyo3"
version = "0.15.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d41d50a7271e08c7c8a54cd24af5d62f73ee3a6f6a314215281ebdec421d5752"
dependencies = [
"cfg-if",
"indoc",
"libc",
"parking_lot",
"paste",
"pyo3-build-config",
"pyo3-macros",
"unindent",
]
[[package]]
name = "pyo3-build-config"
version = "0.15.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "779239fc40b8e18bc8416d3a37d280ca9b9fb04bda54b98037bb6748595c2410"
dependencies = [
"once_cell",
]
[[package]]
name = "pyo3-macros"
version = "0.15.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "00b247e8c664be87998d8628e86f282c25066165f1f8dda66100c48202fdb93a"
dependencies = [
"pyo3-macros-backend",
"quote",
"syn",
]
[[package]]
name = "pyo3-macros-backend"
version = "0.15.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5a8c2812c412e00e641d99eeb79dd478317d981d938aa60325dfa7157b607095"
dependencies = [
"proc-macro2",
"pyo3-build-config",
"quote",
"syn",
]
[[package]]
name = "quote"
version = "1.0.21"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bbe448f377a7d6961e30f5955f9b8d106c3f5e449d493ee1b125c1d43c2b5179"
dependencies = [
"proc-macro2",
]
[[package]]
name = "redox_syscall"
version = "0.2.16"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fb5a58c1855b4b6819d59012155603f0b22ad30cad752600aadfcb695265519a"
dependencies = [
"bitflags",
]
[[package]]
name = "scopeguard"
version = "1.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d29ab0c6d3fc0ee92fe66e2d99f700eab17a8d57d1c1d3b748380fb20baa78cd"
[[package]]
name = "smallvec"
version = "1.9.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2fd0db749597d91ff862fd1d55ea87f7855a744a8425a64695b6fca237d1dad1"
[[package]]
name = "syn"
version = "1.0.99"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "58dbef6ec655055e20b86b15a8cc6d439cca19b667537ac6a1369572d151ab13"
dependencies = [
"proc-macro2",
"quote",
"unicode-ident",
]
[[package]]
name = "unicode-ident"
version = "1.0.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c4f5b37a154999a8f3f98cc23a628d850e154479cd94decf3414696e12e31aaf"
[[package]]
name = "unindent"
version = "0.1.10"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "58ee9362deb4a96cef4d437d1ad49cffc9b9e92d202b6995674e928ce684f112"
[[package]]
name = "winapi"
version = "0.3.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5c839a674fcd7a98952e593242ea400abe93992746761e38641405d28b00f419"
dependencies = [
"winapi-i686-pc-windows-gnu",
"winapi-x86_64-pc-windows-gnu",
]
[[package]]
name = "winapi-i686-pc-windows-gnu"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6"
[[package]]
name = "winapi-x86_64-pc-windows-gnu"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"

View File

@@ -0,0 +1,16 @@
[package]
name = "neon-dev-utils"
version = "0.1.0"
edition = "2021"
[lib]
name = "neon_dev_utils"
# "cdylib" is necessary to produce a shared library for Python to import from.
#
# Downstream Rust code (including code in `bin/`, `examples/`, and `tests/`) will not be able
# to `use string_sum;` unless the "rlib" or "lib" crate type is also included, e.g.:
# crate-type = ["cdylib", "rlib"]
crate-type = ["cdylib"]
[dependencies]
pyo3 = { version = "0.15.1", features = ["extension-module"] }

View File

@@ -0,0 +1,31 @@
[[package]]
name = "maturin"
version = "0.13.2"
description = "Build and publish crates with pyo3, rust-cpython and cffi bindings as well as rust binaries as python packages"
category = "dev"
optional = false
python-versions = ">=3.7"
[package.dependencies]
tomli = {version = ">=1.1.0", markers = "python_version < \"3.11\""}
[package.extras]
zig = ["ziglang (>=0.9.0,<0.10.0)"]
patchelf = ["patchelf"]
[[package]]
name = "tomli"
version = "2.0.1"
description = "A lil' TOML parser"
category = "dev"
optional = false
python-versions = ">=3.7"
[metadata]
lock-version = "1.1"
python-versions = "^3.10"
content-hash = "4e177514d6cf74b58bcd8ca30ef300c10a833b3e6b1d809aa57337ee20efeb47"
[metadata.files]
maturin = []
tomli = []

View File

@@ -0,0 +1,15 @@
[tool.poetry]
name = "neon-dev-utils"
version = "0.1.0"
description = "Python bindings for common neon development utils"
authors = ["Your Name <you@example.com>"]
[tool.poetry.dependencies]
python = "^3.10"
[tool.poetry.dev-dependencies]
maturin = "^0.13.2"
[build-system]
requires = ["maturin>=0.13.2", "poetry-core>=1.0.0"]
build-backend = "maturin"

View File

@@ -0,0 +1,17 @@
use pyo3::prelude::*;
/// Formats the sum of two numbers as string.
#[pyfunction]
fn sum_as_string(a: usize, b: usize) -> PyResult<String> {
Ok((a + b).to_string())
}
/// A Python module implemented in Rust. The name of this function must match
/// the `lib.name` setting in the `Cargo.toml`, else Python will not be able to
/// import the module.
#[pymodule]
fn neon_dev_utils(_py: Python, m: &PyModule) -> PyResult<()> {
m.add_function(wrap_pyfunction!(sum_as_string, m)?)?;
Ok(())
}

188
cli-v2-story.md Normal file
View File

@@ -0,0 +1,188 @@
Create a new Zenith repository in the current directory:
~/git-sandbox/zenith (cli-v2)$ ./target/debug/cli init
The files belonging to this database system will be owned by user "heikki".
This user must also own the server process.
The database cluster will be initialized with locale "en_GB.UTF-8".
The default database encoding has accordingly been set to "UTF8".
The default text search configuration will be set to "english".
Data page checksums are disabled.
creating directory tmp ... ok
creating subdirectories ... ok
selecting dynamic shared memory implementation ... posix
selecting default max_connections ... 100
selecting default shared_buffers ... 128MB
selecting default time zone ... Europe/Helsinki
creating configuration files ... ok
running bootstrap script ... ok
performing post-bootstrap initialization ... ok
syncing data to disk ... ok
initdb: warning: enabling "trust" authentication for local connections
You can change this by editing pg_hba.conf or using the option -A, or
--auth-local and --auth-host, the next time you run initdb.
new zenith repository was created in .zenith
Initially, there is only one branch:
~/git-sandbox/zenith (cli-v2)$ ./target/debug/cli branch
main
Start a local Postgres instance on the branch:
~/git-sandbox/zenith (cli-v2)$ ./target/debug/cli start main
Creating data directory from snapshot at 0/15FFB08...
waiting for server to start....2021-04-13 09:27:43.919 EEST [984664] LOG: starting PostgreSQL 14devel on x86_64-pc-linux-gnu, compiled by gcc (Debian 10.2.1-6) 10.2.1 20210110, 64-bit
2021-04-13 09:27:43.920 EEST [984664] LOG: listening on IPv6 address "::1", port 5432
2021-04-13 09:27:43.920 EEST [984664] LOG: listening on IPv4 address "127.0.0.1", port 5432
2021-04-13 09:27:43.927 EEST [984664] LOG: listening on Unix socket "/tmp/.s.PGSQL.5432"
2021-04-13 09:27:43.939 EEST [984665] LOG: database system was interrupted; last known up at 2021-04-13 09:27:33 EEST
2021-04-13 09:27:43.939 EEST [984665] LOG: creating missing WAL directory "pg_wal/archive_status"
2021-04-13 09:27:44.189 EEST [984665] LOG: database system was not properly shut down; automatic recovery in progress
2021-04-13 09:27:44.195 EEST [984665] LOG: invalid record length at 0/15FFB80: wanted 24, got 0
2021-04-13 09:27:44.195 EEST [984665] LOG: redo is not required
2021-04-13 09:27:44.225 EEST [984664] LOG: database system is ready to accept connections
done
server started
Run some commands against it:
~/git-sandbox/zenith (cli-v2)$ psql postgres -c "create table foo (t text);"
CREATE TABLE
~/git-sandbox/zenith (cli-v2)$ psql postgres -c "insert into foo values ('inserted on the main branch');"
INSERT 0 1
~/git-sandbox/zenith (cli-v2)$ psql postgres -c "select * from foo"
t
-----------------------------
inserted on the main branch
(1 row)
Create a new branch called 'experimental'. We create it from the
current end of the 'main' branch, but you could specify a different
LSN as the start point instead.
~/git-sandbox/zenith (cli-v2)$ ./target/debug/cli branch experimental main
branching at end of WAL: 0/161F478
~/git-sandbox/zenith (cli-v2)$ ./target/debug/cli branch
experimental
main
Start another Postgres instance off the 'experimental' branch:
~/git-sandbox/zenith (cli-v2)$ ./target/debug/cli start experimental -- -o -p5433
Creating data directory from snapshot at 0/15FFB08...
waiting for server to start....2021-04-13 09:28:41.874 EEST [984766] LOG: starting PostgreSQL 14devel on x86_64-pc-linux-gnu, compiled by gcc (Debian 10.2.1-6) 10.2.1 20210110, 64-bit
2021-04-13 09:28:41.875 EEST [984766] LOG: listening on IPv6 address "::1", port 5433
2021-04-13 09:28:41.875 EEST [984766] LOG: listening on IPv4 address "127.0.0.1", port 5433
2021-04-13 09:28:41.883 EEST [984766] LOG: listening on Unix socket "/tmp/.s.PGSQL.5433"
2021-04-13 09:28:41.896 EEST [984767] LOG: database system was interrupted; last known up at 2021-04-13 09:27:33 EEST
2021-04-13 09:28:42.265 EEST [984767] LOG: database system was not properly shut down; automatic recovery in progress
2021-04-13 09:28:42.269 EEST [984767] LOG: redo starts at 0/15FFB80
2021-04-13 09:28:42.272 EEST [984767] LOG: invalid record length at 0/161F4B0: wanted 24, got 0
2021-04-13 09:28:42.272 EEST [984767] LOG: redo done at 0/161F478 system usage: CPU: user: 0.00 s, system: 0.00 s, elapsed: 0.00 s
2021-04-13 09:28:42.321 EEST [984766] LOG: database system is ready to accept connections
done
server started
Insert some a row on the 'experimental' branch:
~/git-sandbox/zenith (cli-v2)$ psql postgres -p5433 -c "select * from foo"
t
-----------------------------
inserted on the main branch
(1 row)
~/git-sandbox/zenith (cli-v2)$ psql postgres -p5433 -c "insert into foo values ('inserted on experimental')"
INSERT 0 1
~/git-sandbox/zenith (cli-v2)$ psql postgres -p5433 -c "select * from foo"
t
-----------------------------
inserted on the main branch
inserted on experimental
(2 rows)
See that the other Postgres instance is still running on 'main' branch on port 5432:
~/git-sandbox/zenith (cli-v2)$ psql postgres -p5432 -c "select * from foo"
t
-----------------------------
inserted on the main branch
(1 row)
Everything is stored in the .zenith directory:
~/git-sandbox/zenith (cli-v2)$ ls -l .zenith/
total 12
drwxr-xr-x 4 heikki heikki 4096 Apr 13 09:28 datadirs
drwxr-xr-x 4 heikki heikki 4096 Apr 13 09:27 refs
drwxr-xr-x 4 heikki heikki 4096 Apr 13 09:28 timelines
The 'datadirs' directory contains the datadirs of the running instances:
~/git-sandbox/zenith (cli-v2)$ ls -l .zenith/datadirs/
total 8
drwx------ 18 heikki heikki 4096 Apr 13 09:27 3c0c634c1674079b2c6d4edf7c91523e
drwx------ 18 heikki heikki 4096 Apr 13 09:28 697e3c103d4b1763cd6e82e4ff361d76
~/git-sandbox/zenith (cli-v2)$ ls -l .zenith/datadirs/3c0c634c1674079b2c6d4edf7c91523e/
total 124
drwxr-xr-x 5 heikki heikki 4096 Apr 13 09:27 base
drwxr-xr-x 2 heikki heikki 4096 Apr 13 09:27 global
drwxr-xr-x 2 heikki heikki 4096 Apr 13 09:27 pg_commit_ts
drwxr-xr-x 2 heikki heikki 4096 Apr 13 09:27 pg_dynshmem
-rw------- 1 heikki heikki 4760 Apr 13 09:27 pg_hba.conf
-rw------- 1 heikki heikki 1636 Apr 13 09:27 pg_ident.conf
drwxr-xr-x 4 heikki heikki 4096 Apr 13 09:32 pg_logical
drwxr-xr-x 4 heikki heikki 4096 Apr 13 09:27 pg_multixact
drwxr-xr-x 2 heikki heikki 4096 Apr 13 09:27 pg_notify
drwxr-xr-x 2 heikki heikki 4096 Apr 13 09:27 pg_replslot
drwxr-xr-x 2 heikki heikki 4096 Apr 13 09:27 pg_serial
drwxr-xr-x 2 heikki heikki 4096 Apr 13 09:27 pg_snapshots
drwxr-xr-x 2 heikki heikki 4096 Apr 13 09:27 pg_stat
drwxr-xr-x 2 heikki heikki 4096 Apr 13 09:34 pg_stat_tmp
drwxr-xr-x 2 heikki heikki 4096 Apr 13 09:27 pg_subtrans
drwxr-xr-x 2 heikki heikki 4096 Apr 13 09:27 pg_tblspc
drwxr-xr-x 2 heikki heikki 4096 Apr 13 09:27 pg_twophase
-rw------- 1 heikki heikki 3 Apr 13 09:27 PG_VERSION
lrwxrwxrwx 1 heikki heikki 52 Apr 13 09:27 pg_wal -> ../../timelines/3c0c634c1674079b2c6d4edf7c91523e/wal
drwxr-xr-x 2 heikki heikki 4096 Apr 13 09:27 pg_xact
-rw------- 1 heikki heikki 88 Apr 13 09:27 postgresql.auto.conf
-rw------- 1 heikki heikki 28688 Apr 13 09:27 postgresql.conf
-rw------- 1 heikki heikki 96 Apr 13 09:27 postmaster.opts
-rw------- 1 heikki heikki 149 Apr 13 09:27 postmaster.pid
Note how 'pg_wal' is just a symlink to the 'timelines' directory. The
datadir is ephemeral, you can delete it at any time, and it can be reconstructed
from the snapshots and WAL stored in the 'timelines' directory. So if you push/pull
the repository, the 'datadirs' are not included. (They are like git working trees)
~/git-sandbox/zenith (cli-v2)$ killall -9 postgres
~/git-sandbox/zenith (cli-v2)$ rm -rf .zenith/datadirs/*
~/git-sandbox/zenith (cli-v2)$ ./target/debug/cli start experimental -- -o -p5433
Creating data directory from snapshot at 0/15FFB08...
waiting for server to start....2021-04-13 09:37:05.476 EEST [985340] LOG: starting PostgreSQL 14devel on x86_64-pc-linux-gnu, compiled by gcc (Debian 10.2.1-6) 10.2.1 20210110, 64-bit
2021-04-13 09:37:05.477 EEST [985340] LOG: listening on IPv6 address "::1", port 5433
2021-04-13 09:37:05.477 EEST [985340] LOG: listening on IPv4 address "127.0.0.1", port 5433
2021-04-13 09:37:05.487 EEST [985340] LOG: listening on Unix socket "/tmp/.s.PGSQL.5433"
2021-04-13 09:37:05.498 EEST [985341] LOG: database system was interrupted; last known up at 2021-04-13 09:27:33 EEST
2021-04-13 09:37:05.808 EEST [985341] LOG: database system was not properly shut down; automatic recovery in progress
2021-04-13 09:37:05.813 EEST [985341] LOG: redo starts at 0/15FFB80
2021-04-13 09:37:05.815 EEST [985341] LOG: invalid record length at 0/161F770: wanted 24, got 0
2021-04-13 09:37:05.815 EEST [985341] LOG: redo done at 0/161F738 system usage: CPU: user: 0.00 s, system: 0.00 s, elapsed: 0.00 s
2021-04-13 09:37:05.866 EEST [985340] LOG: database system is ready to accept connections
done
server started
~/git-sandbox/zenith (cli-v2)$ psql postgres -p5433 -c "select * from foo"
t
-----------------------------
inserted on the main branch
inserted on experimental
(2 rows)

View File

@@ -2,23 +2,20 @@
name = "compute_tools"
version = "0.1.0"
edition = "2021"
license = "Apache-2.0"
[dependencies]
anyhow = "1.0"
chrono = { version = "0.4", default-features = false, features = ["clock"] }
clap = "4.0"
chrono = "0.4"
clap = "3.0"
env_logger = "0.9"
futures = "0.3.13"
hyper = { version = "0.14", features = ["full"] }
log = { version = "0.4", features = ["std", "serde"] }
notify = "5.0.0"
postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e" }
postgres = { git = "https://github.com/zenithdb/rust-postgres.git", rev="d052ee8b86fff9897c77b0fe89ea9daba0e1fa38" }
regex = "1"
serde = { version = "1.0", features = ["derive"] }
serde_json = "1"
tar = "0.4"
tokio = { version = "1.17", features = ["macros", "rt", "rt-multi-thread"] }
tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev="43e6db254a97fdecbce33d8bc0890accfd74495e" }
tokio-postgres = { git = "https://github.com/zenithdb/rust-postgres.git", rev="d052ee8b86fff9897c77b0fe89ea9daba0e1fa38" }
url = "2.2.2"
workspace_hack = { version = "0.1", path = "../workspace_hack" }

View File

@@ -51,19 +51,53 @@ fn main() -> Result<()> {
// TODO: re-use `utils::logging` later
init_logger(DEFAULT_LOG_LEVEL)?;
let matches = cli().get_matches();
// Env variable is set by `cargo`
let version: Option<&str> = option_env!("CARGO_PKG_VERSION");
let matches = clap::App::new("compute_ctl")
.version(version.unwrap_or("unknown"))
.arg(
Arg::new("connstr")
.short('C')
.long("connstr")
.value_name("DATABASE_URL")
.required(true),
)
.arg(
Arg::new("pgdata")
.short('D')
.long("pgdata")
.value_name("DATADIR")
.required(true),
)
.arg(
Arg::new("pgbin")
.short('b')
.long("pgbin")
.value_name("POSTGRES_PATH"),
)
.arg(
Arg::new("spec")
.short('s')
.long("spec")
.value_name("SPEC_JSON"),
)
.arg(
Arg::new("spec-path")
.short('S')
.long("spec-path")
.value_name("SPEC_PATH"),
)
.get_matches();
let pgdata = matches
.get_one::<String>("pgdata")
.expect("PGDATA path is required");
let pgdata = matches.value_of("pgdata").expect("PGDATA path is required");
let connstr = matches
.get_one::<String>("connstr")
.value_of("connstr")
.expect("Postgres connection string is required");
let spec = matches.get_one::<String>("spec");
let spec_path = matches.get_one::<String>("spec-path");
let spec = matches.value_of("spec");
let spec_path = matches.value_of("spec-path");
// Try to use just 'postgres' if no path is provided
let pgbin = matches.get_one::<String>("pgbin").unwrap();
let pgbin = matches.value_of("pgbin").unwrap_or("postgres");
let spec: ComputeSpec = match spec {
// First, try to get cluster spec from the cli argument
@@ -105,7 +139,7 @@ fn main() -> Result<()> {
tenant,
timeline,
pageserver_connstr,
metrics: ComputeMetrics::default(),
metrics: ComputeMetrics::new(),
state: RwLock::new(ComputeState::new()),
};
let compute = Arc::new(compute_state);
@@ -139,48 +173,3 @@ fn main() -> Result<()> {
}
}
}
fn cli() -> clap::Command {
// Env variable is set by `cargo`
let version = option_env!("CARGO_PKG_VERSION").unwrap_or("unknown");
clap::Command::new("compute_ctl")
.version(version)
.arg(
Arg::new("connstr")
.short('C')
.long("connstr")
.value_name("DATABASE_URL")
.required(true),
)
.arg(
Arg::new("pgdata")
.short('D')
.long("pgdata")
.value_name("DATADIR")
.required(true),
)
.arg(
Arg::new("pgbin")
.short('b')
.long("pgbin")
.default_value("postgres")
.value_name("POSTGRES_PATH"),
)
.arg(
Arg::new("spec")
.short('s')
.long("spec")
.value_name("SPEC_JSON"),
)
.arg(
Arg::new("spec-path")
.short('S')
.long("spec-path")
.value_name("SPEC_PATH"),
)
}
#[test]
fn verify_cli() {
cli().debug_assert()
}

View File

@@ -5,7 +5,7 @@ use tokio_postgres::NoTls;
use crate::compute::ComputeNode;
pub fn create_writability_check_data(client: &mut Client) -> Result<()> {
pub fn create_writablity_check_data(client: &mut Client) -> Result<()> {
let query = "
CREATE TABLE IF NOT EXISTS health_check (
id serial primary key,

View File

@@ -23,11 +23,11 @@ use std::sync::RwLock;
use anyhow::{Context, Result};
use chrono::{DateTime, Utc};
use log::{info, warn};
use log::info;
use postgres::{Client, NoTls};
use serde::{Serialize, Serializer};
use crate::checker::create_writability_check_data;
use crate::checker::create_writablity_check_data;
use crate::config;
use crate::pg_helpers::*;
use crate::spec::*;
@@ -91,7 +91,7 @@ pub enum ComputeStatus {
Failed,
}
#[derive(Default, Serialize)]
#[derive(Serialize)]
pub struct ComputeMetrics {
pub sync_safekeepers_ms: AtomicU64,
pub basebackup_ms: AtomicU64,
@@ -99,6 +99,23 @@ pub struct ComputeMetrics {
pub total_startup_ms: AtomicU64,
}
impl ComputeMetrics {
pub fn new() -> Self {
Self {
sync_safekeepers_ms: AtomicU64::new(0),
basebackup_ms: AtomicU64::new(0),
config_ms: AtomicU64::new(0),
total_startup_ms: AtomicU64::new(0),
}
}
}
impl Default for ComputeMetrics {
fn default() -> Self {
Self::new()
}
}
impl ComputeNode {
pub fn set_status(&self, status: ComputeStatus) {
self.state.write().unwrap().status = status;
@@ -158,7 +175,7 @@ impl ComputeNode {
let start_time = Utc::now();
let sync_handle = Command::new(&self.pgbin)
.args(["--sync-safekeepers"])
.args(&["--sync-safekeepers"])
.env("PGDATA", &self.pgdata) // we cannot use -D in this mode
.stdout(Stdio::piped())
.spawn()
@@ -170,13 +187,10 @@ impl ComputeNode {
let sync_output = sync_handle
.wait_with_output()
.expect("postgres --sync-safekeepers failed");
if !sync_output.status.success() {
anyhow::bail!(
"postgres --sync-safekeepers exited with non-zero status: {}. stdout: {}",
"postgres --sync-safekeepers exited with non-zero status: {}",
sync_output.status,
String::from_utf8(sync_output.stdout)
.expect("postgres --sync-safekeepers exited, and stdout is not utf-8"),
);
}
@@ -236,11 +250,18 @@ impl ComputeNode {
// Run postgres as a child process.
let mut pg = Command::new(&self.pgbin)
.args(["-D", &self.pgdata])
.args(&["-D", &self.pgdata])
.spawn()
.expect("cannot start postgres process");
wait_for_postgres(&mut pg, pgdata_path)?;
// Try default Postgres port if it is not provided
let port = self
.spec
.cluster
.settings
.find("port")
.unwrap_or_else(|| "5432".to_string());
wait_for_postgres(&mut pg, &port, pgdata_path)?;
// If connection fails,
// it may be the old node with `zenith_admin` superuser.
@@ -275,7 +296,7 @@ impl ComputeNode {
handle_databases(&self.spec, &mut client)?;
handle_role_deletions(self, &mut client)?;
handle_grants(self, &mut client)?;
create_writability_check_data(&mut client)?;
create_writablity_check_data(&mut client)?;
// 'Close' connection
drop(client);
@@ -311,9 +332,6 @@ impl ComputeNode {
.wait()
.expect("failed to start waiting on Postgres process");
self.check_for_core_dumps()
.expect("failed to check for core dumps");
Ok(ecode)
}
@@ -329,68 +347,4 @@ impl ComputeNode {
self.prepare_pgdata()?;
self.run()
}
// Look for core dumps and collect backtraces.
//
// EKS worker nodes have following core dump settings:
// /proc/sys/kernel/core_pattern -> core
// /proc/sys/kernel/core_uses_pid -> 1
// ulimint -c -> unlimited
// which results in core dumps being written to postgres data directory as core.<pid>.
//
// Use that as a default location and pattern, except macos where core dumps are written
// to /cores/ directory by default.
fn check_for_core_dumps(&self) -> Result<()> {
let core_dump_dir = match std::env::consts::OS {
"macos" => Path::new("/cores/"),
_ => Path::new(&self.pgdata),
};
// Collect core dump paths if any
info!("checking for core dumps in {}", core_dump_dir.display());
let files = fs::read_dir(core_dump_dir)?;
let cores = files.filter_map(|entry| {
let entry = entry.ok()?;
let _ = entry.file_name().to_str()?.strip_prefix("core.")?;
Some(entry.path())
});
// Print backtrace for each core dump
for core_path in cores {
warn!(
"core dump found: {}, collecting backtrace",
core_path.display()
);
// Try first with gdb
let backtrace = Command::new("gdb")
.args(["--batch", "-q", "-ex", "bt", &self.pgbin])
.arg(&core_path)
.output();
// Try lldb if no gdb is found -- that is handy for local testing on macOS
let backtrace = match backtrace {
Err(ref e) if e.kind() == std::io::ErrorKind::NotFound => {
warn!("cannot find gdb, trying lldb");
Command::new("lldb")
.arg("-c")
.arg(&core_path)
.args(["--batch", "-o", "bt all", "-o", "quit"])
.output()
}
_ => backtrace,
}?;
warn!(
"core dump backtrace: {}",
String::from_utf8_lossy(&backtrace.stdout)
);
warn!(
"debugger stderr: {}",
String::from_utf8_lossy(&backtrace.stderr)
);
}
Ok(())
}
}

View File

@@ -9,11 +9,29 @@ use hyper::{Body, Method, Request, Response, Server, StatusCode};
use log::{error, info};
use serde_json;
use crate::compute::ComputeNode;
use crate::compute::{ComputeNode, ComputeStatus};
// Service function to handle all available routes.
async fn routes(req: Request<Body>, compute: Arc<ComputeNode>) -> Response<Body> {
match (req.method(), req.uri().path()) {
// Timestamp of the last Postgres activity in the plain text.
// DEPRECATED in favour of /status
(&Method::GET, "/last_activity") => {
info!("serving /last_active GET request");
let state = compute.state.read().unwrap();
// Use RFC3339 format for consistency.
Response::new(Body::from(state.last_active.to_rfc3339()))
}
// Has compute setup process finished? -> true/false.
// DEPRECATED in favour of /status
(&Method::GET, "/ready") => {
info!("serving /ready GET request");
let status = compute.get_status();
Response::new(Body::from(format!("{}", status == ComputeStatus::Running)))
}
// Serialized compute state.
(&Method::GET, "/status") => {
info!("serving /status GET request");
@@ -28,6 +46,16 @@ async fn routes(req: Request<Body>, compute: Arc<ComputeNode>) -> Response<Body>
Response::new(Body::from(serde_json::to_string(&compute.metrics).unwrap()))
}
// DEPRECATED, use POST instead
(&Method::GET, "/check_writability") => {
info!("serving /check_writability GET request");
let res = crate::checker::check_writability(&compute).await;
match res {
Ok(_) => Response::new(Body::from("true")),
Err(e) => Response::new(Body::from(e.to_string())),
}
}
(&Method::POST, "/check_writability") => {
info!("serving /check_writability POST request");
let res = crate::checker::check_writability(&compute).await;

View File

@@ -37,7 +37,58 @@ paths:
schema:
$ref: "#/components/schemas/ComputeMetrics"
/ready:
get:
deprecated: true
tags:
- "info"
summary: Check whether compute startup process finished successfully
description: ""
operationId: computeIsReady
responses:
"200":
description: Compute is ready ('true') or not ('false')
content:
text/plain:
schema:
type: string
example: "true"
/last_activity:
get:
deprecated: true
tags:
- "info"
summary: Get timestamp of the last compute activity
description: ""
operationId: getLastComputeActivityTS
responses:
"200":
description: Timestamp of the last compute activity
content:
text/plain:
schema:
type: string
example: "2022-10-12T07:20:50.52Z"
/check_writability:
get:
deprecated: true
tags:
- "check"
summary: Check that we can write new data on this compute
description: ""
operationId: checkComputeWritabilityDeprecated
responses:
"200":
description: Check result
content:
text/plain:
schema:
type: string
description: Error text or 'true' if check passed
example: "true"
post:
tags:
- "check"

View File

@@ -74,8 +74,10 @@ fn watch_compute_activity(compute: &ComputeNode) {
}
}
// Get idle backend `state_change` with the max timestamp.
if let Some(last) = idle_backs.iter().max() {
// Sort idle backend `state_change` timestamps. The last one corresponds
// to the last activity.
idle_backs.sort();
if let Some(last) = idle_backs.last() {
last_active = *last;
}
}

View File

@@ -1,18 +1,18 @@
use std::fmt::Write;
use std::fs;
use std::fs::File;
use std::io::{BufRead, BufReader};
use std::net::{SocketAddr, TcpStream};
use std::os::unix::fs::PermissionsExt;
use std::path::Path;
use std::process::Child;
use std::time::{Duration, Instant};
use std::str::FromStr;
use std::{fs, thread, time};
use anyhow::{bail, Result};
use notify::{RecursiveMode, Watcher};
use postgres::{Client, Transaction};
use serde::Deserialize;
const POSTGRES_WAIT_TIMEOUT: Duration = Duration::from_millis(60 * 1000); // milliseconds
const POSTGRES_WAIT_TIMEOUT: u64 = 60 * 1000; // milliseconds
/// Rust representation of Postgres role info with only those fields
/// that matter for us.
@@ -62,16 +62,9 @@ impl GenericOption {
/// Represent `GenericOption` as configuration option.
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!("{} = '{}'", name, val),
_ => format!("{} = {}", name, val),
"string" => format!("{} = '{}'", self.name, val),
_ => format!("{} = {}", self.name, val),
}
} else {
self.name.to_owned()
@@ -119,9 +112,16 @@ pub trait GenericOptionsSearch {
impl GenericOptionsSearch for GenericOptions {
/// Lookup option by name
fn find(&self, name: &str) -> Option<String> {
let ops = self.as_ref()?;
let op = ops.iter().find(|s| s.name == name)?;
op.value.clone()
match &self {
Some(ops) => {
let op = ops.iter().find(|s| s.name == name);
match op {
Some(op) => op.value.clone(),
None => None,
}
}
None => None,
}
}
}
@@ -154,14 +154,6 @@ impl Role {
}
impl Database {
pub fn new(name: PgIdent, owner: PgIdent) -> Self {
Self {
name,
owner,
options: None,
}
}
/// 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
@@ -169,7 +161,7 @@ impl Database {
/// it may require a proper quoting too.
pub fn to_pg_options(&self) -> String {
let mut params: String = self.options.as_pg_options();
write!(params, " OWNER {}", &self.owner.pg_quote())
write!(params, " OWNER {}", &self.owner.quote())
.expect("String is documented to not to error during write operations");
params
@@ -180,17 +172,18 @@ impl Database {
/// 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 {
fn pg_quote(&self) -> String;
/// Generic trait used to provide quoting for strings used in the
/// Postgres SQL queries. Currently used only to implement quoting
/// of identifiers, but could be used for literals in the future.
pub trait PgQuote {
fn quote(&self) -> String;
}
impl Escaping for PgIdent {
impl PgQuote for PgIdent {
/// This is intended to mimic Postgres quote_ident(), but for simplicity it
/// always quotes provided string with `""` and escapes every `"`.
/// **Not idempotent**, i.e. if string is already escaped it will be escaped again.
fn pg_quote(&self) -> String {
/// always quotes provided string with `""` and escapes every `"`. Not idempotent,
/// i.e. if string is already escaped it will be escaped again.
fn quote(&self) -> String {
let result = format!("\"{}\"", self.replace('"', "\"\""));
result
}
@@ -220,118 +213,62 @@ pub fn get_existing_dbs(client: &mut Client) -> Result<Vec<Database>> {
&[],
)?
.iter()
.map(|row| Database::new(row.get("datname"), row.get("owner")))
.map(|row| Database {
name: row.get("datname"),
owner: row.get("owner"),
options: None,
})
.collect();
Ok(postgres_dbs)
}
/// 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'.
pub fn wait_for_postgres(pg: &mut Child, pgdata: &Path) -> Result<()> {
/// Wait for Postgres to become ready to accept connections:
/// - state should be `ready` in the `pgdata/postmaster.pid`
/// - and we should be able to connect to 127.0.0.1:5432
pub fn wait_for_postgres(pg: &mut Child, port: &str, pgdata: &Path) -> Result<()> {
let pid_path = pgdata.join("postmaster.pid");
let mut slept: u64 = 0; // ms
let pause = time::Duration::from_millis(100);
// PostgreSQL writes line "ready" to the postmaster.pid file, when it has
// completed initialization and is ready to accept connections. We want to
// react quickly and perform the rest of our initialization as soon as
// PostgreSQL starts accepting connections. Use 'notify' to be notified
// whenever the PID file is changed, and whenever it changes, read it to
// check if it's now "ready".
//
// You cannot actually watch a file before it exists, so we first watch the
// data directory, and once the postmaster.pid file appears, we switch to
// watch the file instead. We also wake up every 100 ms to poll, just in
// case we miss some events for some reason. Not strictly necessary, but
// better safe than sorry.
let (tx, rx) = std::sync::mpsc::channel();
let (mut watcher, rx): (Box<dyn Watcher>, _) = match notify::recommended_watcher(move |res| {
let _ = tx.send(res);
}) {
Ok(watcher) => (Box::new(watcher), rx),
Err(e) => {
match e.kind {
notify::ErrorKind::Io(os) if os.raw_os_error() == Some(38) => {
// docker on m1 macs does not support recommended_watcher
// but return "Function not implemented (os error 38)"
// see https://github.com/notify-rs/notify/issues/423
let (tx, rx) = std::sync::mpsc::channel();
let timeout = time::Duration::from_millis(10);
let addr = SocketAddr::from_str(&format!("127.0.0.1:{}", port)).unwrap();
// let's poll it faster than what we check the results for (100ms)
let config =
notify::Config::default().with_poll_interval(Duration::from_millis(50));
let watcher = notify::PollWatcher::new(
move |res| {
let _ = tx.send(res);
},
config,
)?;
(Box::new(watcher), rx)
}
_ => return Err(e.into()),
}
}
};
watcher.watch(pgdata, RecursiveMode::NonRecursive)?;
let started_at = Instant::now();
let mut postmaster_pid_seen = false;
loop {
// Sleep POSTGRES_WAIT_TIMEOUT at max (a bit longer actually if consider a TCP timeout,
// but postgres starts listening almost immediately, even if it is not really
// ready to accept connections).
if slept >= POSTGRES_WAIT_TIMEOUT {
bail!("timed out while waiting for Postgres to start");
}
if let Ok(Some(status)) = pg.try_wait() {
// Postgres exited, that is not what we expected, bail out earlier.
let code = status.code().unwrap_or(-1);
bail!("Postgres exited unexpectedly with code {}", code);
}
let res = rx.recv_timeout(Duration::from_millis(100));
log::debug!("woken up by notify: {res:?}");
// If there are multiple events in the channel already, we only need to be
// check once. Swallow the extra events before we go ahead to check the
// pid file.
while let Ok(res) = rx.try_recv() {
log::debug!("swallowing extra event: {res:?}");
}
// Check that we can open pid file first.
if let Ok(file) = File::open(&pid_path) {
if !postmaster_pid_seen {
log::debug!("postmaster.pid appeared");
watcher
.unwatch(pgdata)
.expect("Failed to remove pgdata dir watch");
watcher
.watch(&pid_path, RecursiveMode::NonRecursive)
.expect("Failed to add postmaster.pid file watch");
postmaster_pid_seen = true;
}
let file = BufReader::new(file);
let last_line = file.lines().last();
// Pid file could be there and we could read it, but it could be empty, for example.
if let Some(Ok(line)) = last_line {
let status = line.trim();
log::debug!("last line of postmaster.pid: {status:?}");
let can_connect = TcpStream::connect_timeout(&addr, timeout).is_ok();
// Now Postgres is ready to accept connections
if status == "ready" {
if status == "ready" && can_connect {
break;
}
}
}
// Give up after POSTGRES_WAIT_TIMEOUT.
let duration = started_at.elapsed();
if duration >= POSTGRES_WAIT_TIMEOUT {
bail!("timed out while waiting for Postgres to start");
}
thread::sleep(pause);
slept += 100;
}
log::info!("PostgreSQL is now running, continuing to configure it");
Ok(())
}

View File

@@ -1,9 +1,7 @@
use std::path::Path;
use std::str::FromStr;
use anyhow::Result;
use log::{info, log_enabled, warn, Level};
use postgres::config::Config;
use postgres::{Client, NoTls};
use serde::Deserialize;
@@ -117,8 +115,8 @@ pub fn handle_roles(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
if existing_roles.iter().any(|r| r.name == op.name) {
let query: String = format!(
"ALTER ROLE {} RENAME TO {}",
op.name.pg_quote(),
new_name.pg_quote()
op.name.quote(),
new_name.quote()
);
warn!("renaming role '{}' to '{}'", op.name, new_name);
@@ -164,7 +162,7 @@ pub fn handle_roles(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
}
if update_role {
let mut query: String = format!("ALTER ROLE {} ", name.pg_quote());
let mut query: String = format!("ALTER ROLE {} ", name.quote());
info_print!(" -> update");
query.push_str(&role.to_pg_options());
@@ -172,7 +170,7 @@ pub fn handle_roles(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
}
} else {
info!("role name: '{}'", &name);
let mut query: String = format!("CREATE ROLE {} ", name.pg_quote());
let mut query: String = format!("CREATE ROLE {} ", name.quote());
info!("role create query: '{}'", &query);
info_print!(" -> create");
@@ -181,7 +179,7 @@ pub fn handle_roles(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
let grant_query = format!(
"GRANT pg_read_all_data, pg_write_all_data TO {}",
name.pg_quote()
name.quote()
);
xact.execute(grant_query.as_str(), &[])?;
info!("role grant query: '{}'", &grant_query);
@@ -217,7 +215,7 @@ pub fn handle_role_deletions(node: &ComputeNode, client: &mut Client) -> Result<
// We do not check either role exists or not,
// Postgres will take care of it for us
if op.action == "delete_role" {
let query: String = format!("DROP ROLE IF EXISTS {}", &op.name.pg_quote());
let query: String = format!("DROP ROLE IF EXISTS {}", &op.name.quote());
warn!("deleting role '{}'", &op.name);
xact.execute(query.as_str(), &[])?;
@@ -232,16 +230,17 @@ pub fn handle_role_deletions(node: &ComputeNode, client: &mut Client) -> Result<
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(node.connstr.as_str())?;
conf.dbname(&db.name);
let mut connstr = node.connstr.clone();
// database name is always the last and the only component of the path
connstr.set_path(&db.name);
let mut client = conf.connect(NoTls)?;
let mut client = Client::connect(connstr.as_str(), NoTls)?;
// This will reassign all dependent objects to the db owner
let reassign_query = format!(
"REASSIGN OWNED BY {} TO {}",
role_name.pg_quote(),
db.owner.pg_quote()
role_name.quote(),
db.owner.quote()
);
info!(
"reassigning objects owned by '{}' in db '{}' to '{}'",
@@ -250,7 +249,7 @@ fn reassign_owned_objects(node: &ComputeNode, role_name: &PgIdent) -> Result<()>
client.simple_query(&reassign_query)?;
// This now will only drop privileges of the role
let drop_query = format!("DROP OWNED BY {}", role_name.pg_quote());
let drop_query = format!("DROP OWNED BY {}", role_name.quote());
client.simple_query(&drop_query)?;
}
}
@@ -280,7 +279,7 @@ 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" => {
let query: String = format!("DROP DATABASE IF EXISTS {}", &op.name.pg_quote());
let query: String = format!("DROP DATABASE IF EXISTS {}", &op.name.quote());
warn!("deleting database '{}'", &op.name);
client.execute(query.as_str(), &[])?;
@@ -292,8 +291,8 @@ pub fn handle_databases(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
if existing_dbs.iter().any(|r| r.name == op.name) {
let query: String = format!(
"ALTER DATABASE {} RENAME TO {}",
op.name.pg_quote(),
new_name.pg_quote()
op.name.quote(),
new_name.quote()
);
warn!("renaming database '{}' to '{}'", op.name, new_name);
@@ -321,7 +320,7 @@ pub fn handle_databases(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
// XXX: db owner name is returned as quoted string from Postgres,
// when quoting is needed.
let new_owner = if r.owner.starts_with('"') {
db.owner.pg_quote()
db.owner.quote()
} else {
db.owner.clone()
};
@@ -329,15 +328,15 @@ pub fn handle_databases(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
if new_owner != r.owner {
let query: String = format!(
"ALTER DATABASE {} OWNER TO {}",
name.pg_quote(),
db.owner.pg_quote()
name.quote(),
db.owner.quote()
);
info_print!(" -> update");
client.execute(query.as_str(), &[])?;
}
} else {
let mut query: String = format!("CREATE DATABASE {} ", name.pg_quote());
let mut query: String = format!("CREATE DATABASE {} ", name.quote());
info_print!(" -> create");
query.push_str(&db.to_pg_options());
@@ -367,7 +366,7 @@ pub fn handle_grants(node: &ComputeNode, client: &mut Client) -> Result<()> {
.cluster
.roles
.iter()
.map(|r| r.name.pg_quote())
.map(|r| r.name.quote())
.collect::<Vec<_>>();
for db in &spec.cluster.databases {
@@ -375,7 +374,7 @@ pub fn handle_grants(node: &ComputeNode, client: &mut Client) -> Result<()> {
let query: String = format!(
"GRANT CREATE ON DATABASE {} TO {}",
dbname.pg_quote(),
dbname.quote(),
roles.join(", ")
);
info!("grant query {}", &query);
@@ -386,11 +385,12 @@ pub fn handle_grants(node: &ComputeNode, client: &mut Client) -> Result<()> {
// 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.
let mut db_connstr = node.connstr.clone();
for db in &node.spec.cluster.databases {
let mut conf = Config::from_str(node.connstr.as_str())?;
conf.dbname(&db.name);
// database name is always the last and the only component of the path
db_connstr.set_path(&db.name);
let mut db_client = conf.connect(NoTls)?;
let mut db_client = Client::connect(db_connstr.as_str(), NoTls)?;
// This will only change ownership on the schema itself, not the objects
// inside it. Without it owner of the `public` schema will be `cloud_admin`
@@ -419,36 +419,9 @@ pub fn handle_grants(node: &ComputeNode, client: &mut Client) -> Result<()> {
END IF;\n\
END\n\
$$;",
db.owner.pg_quote()
db.owner.quote()
);
db_client.simple_query(&alter_query)?;
// Explicitly grant CREATE ON SCHEMA PUBLIC to the web_access user.
// This is needed because since postgres 15 this privilege is removed by default.
let grant_query = "DO $$\n\
BEGIN\n\
IF EXISTS(\n\
SELECT nspname\n\
FROM pg_catalog.pg_namespace\n\
WHERE nspname = 'public'\n\
) AND\n\
current_setting('server_version_num')::int/10000 >= 15\n\
THEN\n\
IF EXISTS(\n\
SELECT rolname\n\
FROM pg_catalog.pg_roles\n\
WHERE rolname = 'web_access'\n\
)\n\
THEN\n\
GRANT CREATE ON SCHEMA public TO web_access;\n\
END IF;\n\
END IF;\n\
END\n\
$$;"
.to_string();
info!("grant query for db {} : {}", &db.name, &grant_query);
db_client.simple_query(&grant_query)?;
}
Ok(())

View File

@@ -85,7 +85,7 @@
"vartype": "bool"
},
{
"name": "neon.safekeepers",
"name": "safekeepers",
"value": "127.0.0.1:6502,127.0.0.1:6503,127.0.0.1:6501",
"vartype": "string"
},
@@ -181,6 +181,7 @@
}
]
},
"delta_operations": [
{
"action": "delete_db",

View File

@@ -28,43 +28,14 @@ mod pg_helpers_tests {
assert_eq!(
spec.cluster.settings.as_pg_settings(),
"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'"
"fsync = off\nwal_level = replica\nhot_standby = on\nsafekeepers = '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'"
);
}
#[test]
fn ident_pg_quote() {
fn quote_ident() {
let ident: PgIdent = PgIdent::from("\"name\";\\n select 1;");
assert_eq!(ident.pg_quote(), "\"\"\"name\"\";\\n select 1;\"");
}
#[test]
fn generic_options_search() {
let generic_options: GenericOptions = Some(vec![
GenericOption {
name: "present_value".into(),
value: Some("value".into()),
vartype: "string".into(),
},
GenericOption {
name: "missed_value".into(),
value: None,
vartype: "int".into(),
},
]);
assert_eq!(generic_options.find("present_value"), Some("value".into()));
assert_eq!(generic_options.find("missed_value"), None);
assert_eq!(generic_options.find("invalid_value"), None);
let empty_generic_options: GenericOptions = Some(vec![]);
assert_eq!(empty_generic_options.find("present_value"), None);
assert_eq!(empty_generic_options.find("missed_value"), None);
assert_eq!(empty_generic_options.find("invalid_value"), None);
let none_generic_options: GenericOptions = None;
assert_eq!(none_generic_options.find("present_value"), None);
assert_eq!(none_generic_options.find("missed_value"), None);
assert_eq!(none_generic_options.find("invalid_value"), None);
assert_eq!(ident.quote(), "\"\"\"name\"\";\\n select 1;\"");
}
}

View File

@@ -2,31 +2,21 @@
name = "control_plane"
version = "0.1.0"
edition = "2021"
license = "Apache-2.0"
[dependencies]
anyhow = "1.0"
clap = "4.0"
comfy-table = "6.1"
git-version = "0.3.5"
nix = "0.25"
once_cell = "1.13.0"
postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev = "43e6db254a97fdecbce33d8bc0890accfd74495e" }
regex = "1"
reqwest = { version = "0.11", default-features = false, features = ["blocking", "json", "rustls-tls"] }
serde = { version = "1.0", features = ["derive"] }
serde_with = "2.0"
tar = "0.4.38"
thiserror = "1"
postgres = { git = "https://github.com/zenithdb/rust-postgres.git", rev="d052ee8b86fff9897c77b0fe89ea9daba0e1fa38" }
serde = { version = "1.0", features = ["derive"] }
serde_with = "1.12.0"
toml = "0.5"
url = "2.2.2"
once_cell = "1.13.0"
regex = "1"
anyhow = "1.0"
thiserror = "1"
nix = "0.23"
reqwest = { version = "0.11", default-features = false, features = ["blocking", "json", "rustls-tls"] }
# Note: Do not directly depend on pageserver or safekeeper; use pageserver_api or safekeeper_api
# instead, so that recompile times are better.
pageserver_api = { path = "../libs/pageserver_api" }
postgres_connection = { path = "../libs/postgres_connection" }
safekeeper_api = { path = "../libs/safekeeper_api" }
# Note: main broker code is inside the binary crate, so linking with the library shouldn't be heavy.
storage_broker = { version = "0.1", path = "../storage_broker" }
pageserver = { path = "../pageserver" }
safekeeper = { path = "../safekeeper" }
utils = { path = "../libs/utils" }
workspace_hack = { version = "0.1", path = "../workspace_hack" }

View File

@@ -1,4 +1,4 @@
# Minimal neon environment with one safekeeper. This is equivalent to the built-in
# Minimal zenith environment with one safekeeper. This is equivalent to the built-in
# defaults that you get with no --config
[pageserver]
listen_pg_addr = '127.0.0.1:64000'
@@ -10,5 +10,5 @@ id = 1
pg_port = 5454
http_port = 7676
[broker]
listen_addr = '127.0.0.1:50051'
[etcd_broker]
broker_endpoints = ['http://127.0.0.1:2379']

View File

@@ -1,353 +0,0 @@
//! Spawns and kills background processes that are needed by Neon CLI.
//! Applies common set-up such as log and pid files (if needed) to every process.
//!
//! Neon CLI does not run in background, so it needs to store the information about
//! spawned processes, which it does in this module.
//! We do that by storing the pid of the process in the "${process_name}.pid" file.
//! The pid file can be created by the process itself
//! (Neon storage binaries do that and also ensure that a lock is taken onto that file)
//! or we create such file after starting the process
//! (non-Neon binaries don't necessarily follow our pidfile conventions).
//! The pid stored in the file is later used to stop the service.
//!
//! See [`lock_file`] module for more info.
use std::ffi::OsStr;
use std::io::Write;
use std::os::unix::prelude::AsRawFd;
use std::os::unix::process::CommandExt;
use std::path::{Path, PathBuf};
use std::process::{Child, Command};
use std::time::Duration;
use std::{fs, io, thread};
use anyhow::Context;
use nix::errno::Errno;
use nix::fcntl::{FcntlArg, FdFlag};
use nix::sys::signal::{kill, Signal};
use nix::unistd::Pid;
use utils::pid_file::{self, PidFileRead};
// These constants control the loop used to poll for process start / stop.
//
// The loop waits for at most 10 seconds, polling every 100 ms.
// Once a second, it prints a dot ("."), to give the user an indication that
// it's waiting. If the process hasn't started/stopped after 5 seconds,
// it prints a notice that it's taking long, but keeps waiting.
//
const RETRY_UNTIL_SECS: u64 = 10;
const RETRIES: u64 = (RETRY_UNTIL_SECS * 1000) / RETRY_INTERVAL_MILLIS;
const RETRY_INTERVAL_MILLIS: u64 = 100;
const DOT_EVERY_RETRIES: u64 = 10;
const NOTICE_AFTER_RETRIES: u64 = 50;
/// Argument to `start_process`, to indicate whether it should create pidfile or if the process creates
/// it itself.
pub enum InitialPidFile<'t> {
/// Create a pidfile, to allow future CLI invocations to manipulate the process.
Create(&'t Path),
/// The process will create the pidfile itself, need to wait for that event.
Expect(&'t Path),
}
/// Start a background child process using the parameters given.
pub fn start_process<F, AI, A, EI>(
process_name: &str,
datadir: &Path,
command: &Path,
args: AI,
envs: EI,
initial_pid_file: InitialPidFile,
process_status_check: F,
) -> anyhow::Result<Child>
where
F: Fn() -> anyhow::Result<bool>,
AI: IntoIterator<Item = A>,
A: AsRef<OsStr>,
// Not generic AsRef<OsStr>, otherwise empty `envs` prevents type inference
EI: IntoIterator<Item = (String, String)>,
{
let log_path = datadir.join(format!("{process_name}.log"));
let process_log_file = fs::OpenOptions::new()
.create(true)
.write(true)
.append(true)
.open(&log_path)
.with_context(|| {
format!("Could not open {process_name} log file {log_path:?} for writing")
})?;
let same_file_for_stderr = process_log_file.try_clone().with_context(|| {
format!("Could not reuse {process_name} log file {log_path:?} for writing stderr")
})?;
let mut command = Command::new(command);
let background_command = command
.stdout(process_log_file)
.stderr(same_file_for_stderr)
.args(args);
let filled_cmd = fill_aws_secrets_vars(fill_rust_env_vars(background_command));
filled_cmd.envs(envs);
let pid_file_to_check = match initial_pid_file {
InitialPidFile::Create(path) => {
pre_exec_create_pidfile(filled_cmd, path);
path
}
InitialPidFile::Expect(path) => path,
};
let mut spawned_process = filled_cmd.spawn().with_context(|| {
format!("Could not spawn {process_name}, see console output and log files for details.")
})?;
let pid = spawned_process.id();
let pid = Pid::from_raw(
i32::try_from(pid)
.with_context(|| format!("Subprocess {process_name} has invalid pid {pid}"))?,
);
for retries in 0..RETRIES {
match process_started(pid, Some(pid_file_to_check), &process_status_check) {
Ok(true) => {
println!("\n{process_name} started, pid: {pid}");
return Ok(spawned_process);
}
Ok(false) => {
if retries == NOTICE_AFTER_RETRIES {
// The process is taking a long time to start up. Keep waiting, but
// print a message
print!("\n{process_name} has not started yet, continuing to wait");
}
if retries % DOT_EVERY_RETRIES == 0 {
print!(".");
io::stdout().flush().unwrap();
}
thread::sleep(Duration::from_millis(RETRY_INTERVAL_MILLIS));
}
Err(e) => {
println!("{process_name} failed to start: {e:#}");
if let Err(e) = spawned_process.kill() {
println!("Could not stop {process_name} subprocess: {e:#}")
};
return Err(e);
}
}
}
println!();
anyhow::bail!("{process_name} did not start in {RETRY_UNTIL_SECS} seconds");
}
/// Send SIGTERM to child process
pub fn send_stop_child_process(child: &std::process::Child) -> anyhow::Result<()> {
let pid = child.id();
match kill(
nix::unistd::Pid::from_raw(pid.try_into().unwrap()),
Signal::SIGTERM,
) {
Ok(()) => Ok(()),
Err(Errno::ESRCH) => {
println!("child process with pid {pid} does not exist");
Ok(())
}
Err(e) => anyhow::bail!("Failed to send signal to child process with pid {pid}: {e}"),
}
}
/// Stops the process, using the pid file given. Returns Ok also if the process is already not running.
pub fn stop_process(immediate: bool, process_name: &str, pid_file: &Path) -> anyhow::Result<()> {
let pid = match pid_file::read(pid_file)
.with_context(|| format!("read pid_file {pid_file:?}"))?
{
PidFileRead::NotExist => {
println!("{process_name} is already stopped: no pid file present at {pid_file:?}");
return Ok(());
}
PidFileRead::NotHeldByAnyProcess(_) => {
// Don't try to kill according to file contents beacuse the pid might have been re-used by another process.
// Don't delete the file either, it can race with new pid file creation.
// Read `pid_file` module comment for details.
println!(
"No process is holding the pidfile. The process must have already exited. Leave in place to avoid race conditions: {pid_file:?}"
);
return Ok(());
}
PidFileRead::LockedByOtherProcess(pid) => pid,
};
// XXX the pid could become invalid (and recycled) at any time before the kill() below.
// send signal
let sig = if immediate {
print!("Stopping {process_name} with pid {pid} immediately..");
Signal::SIGQUIT
} else {
print!("Stopping {process_name} with pid {pid} gracefully..");
Signal::SIGTERM
};
io::stdout().flush().unwrap();
match kill(pid, sig) {
Ok(()) => (),
Err(Errno::ESRCH) => {
// Again, don't delete the pid file. The unlink can race with a new pid file being created.
println!(
"{process_name} with pid {pid} does not exist, but a pid file {pid_file:?} was found. Likely the pid got recycled. Lucky we didn't harm anyone."
);
return Ok(());
}
Err(e) => anyhow::bail!("Failed to send signal to {process_name} with pid {pid}: {e}"),
}
// Wait until process is gone
for retries in 0..RETRIES {
match process_has_stopped(pid) {
Ok(true) => {
println!("\n{process_name} stopped");
return Ok(());
}
Ok(false) => {
if retries == NOTICE_AFTER_RETRIES {
// The process is taking a long time to start up. Keep waiting, but
// print a message
print!("\n{process_name} has not stopped yet, continuing to wait");
}
if retries % DOT_EVERY_RETRIES == 0 {
print!(".");
io::stdout().flush().unwrap();
}
thread::sleep(Duration::from_millis(RETRY_INTERVAL_MILLIS));
}
Err(e) => {
println!("{process_name} with pid {pid} failed to stop: {e:#}");
return Err(e);
}
}
}
println!();
anyhow::bail!("{process_name} with pid {pid} did not stop in {RETRY_UNTIL_SECS} seconds");
}
fn fill_rust_env_vars(cmd: &mut Command) -> &mut Command {
// If RUST_BACKTRACE is set, pass it through. But if it's not set, default
// to RUST_BACKTRACE=1.
let backtrace_setting = std::env::var_os("RUST_BACKTRACE");
let backtrace_setting = backtrace_setting
.as_deref()
.unwrap_or_else(|| OsStr::new("1"));
let mut filled_cmd = cmd.env_clear().env("RUST_BACKTRACE", backtrace_setting);
// Pass through these environment variables to the command
for var in ["LLVM_PROFILE_FILE", "FAILPOINTS", "RUST_LOG"] {
if let Some(val) = std::env::var_os(var) {
filled_cmd = filled_cmd.env(var, val);
}
}
filled_cmd
}
fn fill_aws_secrets_vars(mut cmd: &mut Command) -> &mut Command {
for env_key in [
"AWS_ACCESS_KEY_ID",
"AWS_SECRET_ACCESS_KEY",
"AWS_SESSION_TOKEN",
] {
if let Ok(value) = std::env::var(env_key) {
cmd = cmd.env(env_key, value);
}
}
cmd
}
/// Add a `pre_exec` to the cmd that, inbetween fork() and exec(),
/// 1. Claims a pidfile with a fcntl lock on it and
/// 2. Sets up the pidfile's file descriptor so that it (and the lock)
/// will remain held until the cmd exits.
fn pre_exec_create_pidfile<P>(cmd: &mut Command, path: P) -> &mut Command
where
P: Into<PathBuf>,
{
let path: PathBuf = path.into();
// SAFETY
// pre_exec is marked unsafe because it runs between fork and exec.
// Why is that dangerous in various ways?
// Long answer: https://github.com/rust-lang/rust/issues/39575
// Short answer: in a multi-threaded program, other threads may have
// been inside of critical sections at the time of fork. In the
// original process, that was allright, assuming they protected
// the critical sections appropriately, e.g., through locks.
// Fork adds another process to the mix that
// 1. Has a single thread T
// 2. In an exact copy of the address space at the time of fork.
// A variety of problems scan occur now:
// 1. T tries to grab a lock that was locked at the time of fork.
// It will wait forever since in its address space, the lock
// is in state 'taken' but the thread that would unlock it is
// not there.
// 2. A rust object that represented some external resource in the
// parent now got implicitly copied by the the fork, even though
// the object's type is not `Copy`. The parent program may use
// non-copyability as way to enforce unique ownership of an
// external resource in the typesystem. The fork breaks that
// assumption, as now both parent and child process have an
// owned instance of the object that represents the same
// underlying resource.
// While these seem like niche problems, (1) in particular is
// highly relevant. For example, `malloc()` may grab a mutex internally,
// and so, if we forked while another thread was mallocing' and our
// pre_exec closure allocates as well, it will block on the malloc
// mutex forever
//
// The proper solution is to only use C library functions that are marked
// "async-signal-safe": https://man7.org/linux/man-pages/man7/signal-safety.7.html
//
// With this specific pre_exec() closure, the non-error path doesn't allocate.
// The error path uses `anyhow`, and hence does allocate.
// We take our chances there, hoping that any potential disaster is constrained
// to the child process (e.g., malloc has no state ourside of the child process).
// Last, `expect` prints to stderr, and stdio is not async-signal-safe.
// Again, we take our chances, making the same assumptions as for malloc.
unsafe {
cmd.pre_exec(move || {
let file = pid_file::claim_for_current_process(&path).expect("claim pid file");
// Remove the FD_CLOEXEC flag on the pidfile descriptor so that the pidfile
// remains locked after exec.
nix::fcntl::fcntl(file.as_raw_fd(), FcntlArg::F_SETFD(FdFlag::empty()))
.expect("remove FD_CLOEXEC");
// Don't run drop(file), it would close the file before we actually exec.
std::mem::forget(file);
Ok(())
});
}
cmd
}
fn process_started<F>(
pid: Pid,
pid_file_to_check: Option<&Path>,
status_check: &F,
) -> anyhow::Result<bool>
where
F: Fn() -> anyhow::Result<bool>,
{
match status_check() {
Ok(true) => match pid_file_to_check {
Some(pid_file_path) => match pid_file::read(pid_file_path)? {
PidFileRead::NotExist => Ok(false),
PidFileRead::LockedByOtherProcess(pid_in_file) => Ok(pid_in_file == pid),
PidFileRead::NotHeldByAnyProcess(_) => Ok(false),
},
None => Ok(true),
},
Ok(false) => Ok(false),
Err(e) => anyhow::bail!("process failed to start: {e}"),
}
}
fn process_has_stopped(pid: Pid) -> anyhow::Result<bool> {
match kill(pid, None) {
// Process exists, keep waiting
Ok(_) => Ok(false),
// Process not found, we're done
Err(Errno::ESRCH) => Ok(true),
Err(err) => anyhow::bail!("Failed to send signal to process with pid {pid}: {err}"),
}
}

View File

@@ -1,48 +0,0 @@
use anyhow::Context;
use std::path::PathBuf;
use crate::{background_process, local_env};
pub fn start_broker_process(env: &local_env::LocalEnv) -> anyhow::Result<()> {
let broker = &env.broker;
let listen_addr = &broker.listen_addr;
print!("Starting neon broker at {}", listen_addr);
let args = [format!("--listen-addr={listen_addr}")];
let client = reqwest::blocking::Client::new();
background_process::start_process(
"storage_broker",
&env.base_data_dir,
&env.storage_broker_bin(),
args,
[],
background_process::InitialPidFile::Create(&storage_broker_pid_file_path(env)),
|| {
let url = broker.client_url();
let status_url = url.join("status").with_context(|| {
format!("Failed to append /status path to broker endpoint {url}",)
})?;
let request = client
.get(status_url)
.build()
.with_context(|| format!("Failed to construct request to broker endpoint {url}"))?;
match client.execute(request) {
Ok(resp) => Ok(resp.status().is_success()),
Err(_) => Ok(false),
}
},
)
.context("Failed to spawn storage_broker subprocess")?;
Ok(())
}
pub fn stop_broker_process(env: &local_env::LocalEnv) -> anyhow::Result<()> {
background_process::stop_process(true, "storage_broker", &storage_broker_pid_file_path(env))
}
fn storage_broker_pid_file_path(env: &local_env::LocalEnv) -> PathBuf {
env.base_data_dir.join("storage_broker.pid")
}

View File

@@ -12,14 +12,15 @@ use std::time::Duration;
use anyhow::{Context, Result};
use utils::{
id::{TenantId, TimelineId},
connstring::connection_host_port,
lsn::Lsn,
postgres_backend::AuthType,
zid::{ZTenantId, ZTimelineId},
};
use crate::local_env::{LocalEnv, DEFAULT_PG_VERSION};
use crate::pageserver::PageServerNode;
use crate::local_env::LocalEnv;
use crate::postgresql_conf::PostgresConf;
use crate::storage::PageServerNode;
//
// ComputeControlPlane
@@ -27,7 +28,7 @@ use crate::postgresql_conf::PostgresConf;
pub struct ComputeControlPlane {
base_port: u16,
pageserver: Arc<PageServerNode>,
pub nodes: BTreeMap<(TenantId, String), Arc<PostgresNode>>,
pub nodes: BTreeMap<(ZTenantId, String), Arc<PostgresNode>>,
env: LocalEnv,
}
@@ -44,7 +45,7 @@ impl ComputeControlPlane {
let mut nodes = BTreeMap::default();
let pgdatadirspath = &env.pg_data_dirs_path();
for tenant_dir in fs::read_dir(pgdatadirspath)
for tenant_dir in fs::read_dir(&pgdatadirspath)
.with_context(|| format!("failed to list {}", pgdatadirspath.display()))?
{
let tenant_dir = tenant_dir?;
@@ -67,20 +68,19 @@ impl ComputeControlPlane {
fn get_port(&mut self) -> u16 {
1 + self
.nodes
.values()
.map(|node| node.address.port())
.iter()
.map(|(_name, node)| node.address.port())
.max()
.unwrap_or(self.base_port)
}
pub fn new_node(
&mut self,
tenant_id: TenantId,
tenant_id: ZTenantId,
name: &str,
timeline_id: TimelineId,
timeline_id: ZTimelineId,
lsn: Option<Lsn>,
port: Option<u16>,
pg_version: u32,
) -> Result<Arc<PostgresNode>> {
let port = port.unwrap_or_else(|| self.get_port());
let node = Arc::new(PostgresNode {
@@ -93,7 +93,6 @@ impl ComputeControlPlane {
lsn,
tenant_id,
uses_wal_proposer: false,
pg_version,
});
node.create_pgdata()?;
@@ -115,11 +114,10 @@ pub struct PostgresNode {
pub env: LocalEnv,
pageserver: Arc<PageServerNode>,
is_test: bool,
pub timeline_id: TimelineId,
pub timeline_id: ZTimelineId,
pub lsn: Option<Lsn>, // if it's a read-only node. None for primary
pub tenant_id: TenantId,
pub tenant_id: ZTenantId,
uses_wal_proposer: bool,
pg_version: u32,
}
impl PostgresNode {
@@ -150,17 +148,9 @@ impl PostgresNode {
// Read a few options from the config file
let context = format!("in config file {}", cfg_path_str);
let port: u16 = conf.parse_field("port", &context)?;
let timeline_id: TimelineId = conf.parse_field("neon.timeline_id", &context)?;
let tenant_id: TenantId = conf.parse_field("neon.tenant_id", &context)?;
let uses_wal_proposer = conf.get("neon.safekeepers").is_some();
// Read postgres version from PG_VERSION file to determine which postgres version binary to use.
// If it doesn't exist, assume broken data directory and use default pg version.
let pg_version_path = entry.path().join("PG_VERSION");
let pg_version_str =
fs::read_to_string(pg_version_path).unwrap_or_else(|_| DEFAULT_PG_VERSION.to_string());
let pg_version = u32::from_str(&pg_version_str)?;
let timeline_id: ZTimelineId = conf.parse_field("neon.timeline_id", &context)?;
let tenant_id: ZTenantId = conf.parse_field("neon.tenant_id", &context)?;
let uses_wal_proposer = conf.get("safekeepers").is_some();
// parse recovery_target_lsn, if any
let recovery_target_lsn: Option<Lsn> =
@@ -177,31 +167,24 @@ impl PostgresNode {
lsn: recovery_target_lsn,
tenant_id,
uses_wal_proposer,
pg_version,
})
}
fn sync_safekeepers(&self, auth_token: &Option<String>, pg_version: u32) -> Result<Lsn> {
let pg_path = self.env.pg_bin_dir(pg_version)?.join("postgres");
let mut cmd = Command::new(pg_path);
fn sync_safekeepers(&self, auth_token: &Option<String>) -> Result<Lsn> {
let pg_path = self.env.pg_bin_dir().join("postgres");
let mut cmd = Command::new(&pg_path);
cmd.arg("--sync-safekeepers")
.env_clear()
.env(
"LD_LIBRARY_PATH",
self.env.pg_lib_dir(pg_version)?.to_str().unwrap(),
)
.env(
"DYLD_LIBRARY_PATH",
self.env.pg_lib_dir(pg_version)?.to_str().unwrap(),
)
.env("LD_LIBRARY_PATH", self.env.pg_lib_dir().to_str().unwrap())
.env("DYLD_LIBRARY_PATH", self.env.pg_lib_dir().to_str().unwrap())
.env("PGDATA", self.pgdata().to_str().unwrap())
.stdout(Stdio::piped())
// Comment this to avoid capturing stderr (useful if command hangs)
.stderr(Stdio::piped());
if let Some(token) = auth_token {
cmd.env("NEON_AUTH_TOKEN", token);
cmd.env("ZENITH_AUTH_TOKEN", token);
}
let sync_handle = cmd
@@ -261,7 +244,7 @@ impl PostgresNode {
}
fn create_pgdata(&self) -> Result<()> {
fs::create_dir_all(self.pgdata()).with_context(|| {
fs::create_dir_all(&self.pgdata()).with_context(|| {
format!(
"could not create data directory {}",
self.pgdata().display()
@@ -276,12 +259,14 @@ impl PostgresNode {
})
}
// Write postgresql.conf with default configuration
// and PG_VERSION file to the data directory of a new node.
// Connect to a page server, get base backup, and untar it to initialize a
// new data directory
fn setup_pg_conf(&self, auth_type: AuthType) -> Result<()> {
let mut conf = PostgresConf::new();
conf.append("max_wal_senders", "10");
conf.append("wal_log_hints", "off");
// wal_log_hints is mandatory when running against pageserver (see gh issue#192)
// TODO: is it possible to check wal_log_hints at pageserver side via XLOG_PARAMETER_CHANGE?
conf.append("wal_log_hints", "on");
conf.append("max_replication_slots", "10");
conf.append("hot_standby", "on");
conf.append("shared_buffers", "1MB");
@@ -299,32 +284,28 @@ impl PostgresNode {
// Configure the node to fetch pages from pageserver
let pageserver_connstr = {
let config = &self.pageserver.pg_connection_config;
let (host, port) = (config.host(), config.port());
let (host, port) = connection_host_port(&self.pageserver.pg_connection_config);
// Set up authentication
//
// $NEON_AUTH_TOKEN will be replaced with value from environment
// $ZENITH_AUTH_TOKEN will be replaced with value from environment
// variable during compute pg startup. It is done this way because
// otherwise user will be able to retrieve the value using SHOW
// command or pg_settings
let password = if let AuthType::NeonJWT = auth_type {
"$NEON_AUTH_TOKEN"
let password = if let AuthType::ZenithJWT = auth_type {
"$ZENITH_AUTH_TOKEN"
} else {
""
};
// NOTE avoiding spaces in connection string, because it is less error prone if we forward it somewhere.
// Also note that not all parameters are supported here. Because in compute we substitute $NEON_AUTH_TOKEN
// Also note that not all parameters are supported here. Because in compute we substitute $ZENITH_AUTH_TOKEN
// We parse this string and build it back with token from env var, and for simplicity rebuild
// uses only needed variables namely host, port, user, password.
format!("postgresql://no_user:{password}@{host}:{port}")
format!("postgresql://no_user:{}@{}:{}", password, host, port)
};
conf.append("shared_preload_libraries", "neon");
conf.append_line("");
conf.append("neon.pageserver_connstring", &pageserver_connstr);
if let AuthType::NeonJWT = auth_type {
conf.append("neon.safekeeper_token_env", "$NEON_AUTH_TOKEN");
}
conf.append("neon.tenant_id", &self.tenant_id.to_string());
conf.append("neon.timeline_id", &self.timeline_id.to_string());
if let Some(lsn) = self.lsn {
@@ -346,7 +327,7 @@ impl PostgresNode {
// To be able to restore database in case of pageserver node crash, safekeeper should not
// remove WAL beyond this point. Too large lag can cause space exhaustion in safekeepers
// (if they are not able to upload WAL to S3).
conf.append("max_replication_write_lag", "15MB");
conf.append("max_replication_write_lag", "500MB");
conf.append("max_replication_flush_lag", "10GB");
if !self.env.safekeepers.is_empty() {
@@ -360,7 +341,7 @@ impl PostgresNode {
.map(|sk| format!("localhost:{}", sk.pg_port))
.collect::<Vec<String>>()
.join(",");
conf.append("neon.safekeepers", &safekeepers);
conf.append("safekeepers", &safekeepers);
} else {
// We only use setup without safekeepers for tests,
// and don't care about data durability on pageserver,
@@ -376,9 +357,6 @@ impl PostgresNode {
let mut file = File::create(self.pgdata().join("postgresql.conf"))?;
file.write_all(conf.to_string().as_bytes())?;
let mut file = File::create(self.pgdata().join("PG_VERSION"))?;
file.write_all(self.pg_version.to_string().as_bytes())?;
Ok(())
}
@@ -390,7 +368,7 @@ impl PostgresNode {
// latest data from the pageserver. That is a bit clumsy but whole bootstrap
// procedure evolves quite actively right now, so let's think about it again
// when things would be more stable (TODO).
let lsn = self.sync_safekeepers(auth_token, self.pg_version)?;
let lsn = self.sync_safekeepers(auth_token)?;
if lsn == Lsn(0) {
None
} else {
@@ -423,7 +401,7 @@ impl PostgresNode {
}
fn pg_ctl(&self, args: &[&str], auth_token: &Option<String>) -> Result<()> {
let pg_ctl_path = self.env.pg_bin_dir(self.pg_version)?.join("pg_ctl");
let pg_ctl_path = self.env.pg_bin_dir().join("pg_ctl");
let mut cmd = Command::new(pg_ctl_path);
cmd.args(
[
@@ -439,16 +417,10 @@ impl PostgresNode {
.concat(),
)
.env_clear()
.env(
"LD_LIBRARY_PATH",
self.env.pg_lib_dir(self.pg_version)?.to_str().unwrap(),
)
.env(
"DYLD_LIBRARY_PATH",
self.env.pg_lib_dir(self.pg_version)?.to_str().unwrap(),
);
.env("LD_LIBRARY_PATH", self.env.pg_lib_dir().to_str().unwrap())
.env("DYLD_LIBRARY_PATH", self.env.pg_lib_dir().to_str().unwrap());
if let Some(token) = auth_token {
cmd.env("NEON_AUTH_TOKEN", token);
cmd.env("ZENITH_AUTH_TOKEN", token);
}
let pg_ctl = cmd.output().context("pg_ctl failed")?;
@@ -478,7 +450,7 @@ impl PostgresNode {
postgresql_conf_path.to_str().unwrap()
)
})?;
fs::remove_dir_all(self.pgdata())?;
fs::remove_dir_all(&self.pgdata())?;
self.create_pgdata()?;
// 2. Bring back config files
@@ -514,7 +486,7 @@ impl PostgresNode {
"Destroying postgres data directory '{}'",
self.pgdata().to_str().unwrap()
);
fs::remove_dir_all(self.pgdata())?;
fs::remove_dir_all(&self.pgdata())?;
} else {
self.pg_ctl(&["stop"], &None)?;
}

97
control_plane/src/etcd.rs Normal file
View File

@@ -0,0 +1,97 @@
use std::{
fs,
path::PathBuf,
process::{Command, Stdio},
};
use anyhow::Context;
use nix::{
sys::signal::{kill, Signal},
unistd::Pid,
};
use crate::{local_env, read_pidfile};
pub fn start_etcd_process(env: &local_env::LocalEnv) -> anyhow::Result<()> {
let etcd_broker = &env.etcd_broker;
println!(
"Starting etcd broker using {}",
etcd_broker.etcd_binary_path.display()
);
let etcd_data_dir = env.base_data_dir.join("etcd");
fs::create_dir_all(&etcd_data_dir).with_context(|| {
format!(
"Failed to create etcd data dir: {}",
etcd_data_dir.display()
)
})?;
let etcd_stdout_file =
fs::File::create(etcd_data_dir.join("etcd.stdout.log")).with_context(|| {
format!(
"Failed to create etcd stout file in directory {}",
etcd_data_dir.display()
)
})?;
let etcd_stderr_file =
fs::File::create(etcd_data_dir.join("etcd.stderr.log")).with_context(|| {
format!(
"Failed to create etcd stderr file in directory {}",
etcd_data_dir.display()
)
})?;
let client_urls = etcd_broker.comma_separated_endpoints();
let etcd_process = Command::new(&etcd_broker.etcd_binary_path)
.args(&[
format!("--data-dir={}", etcd_data_dir.display()),
format!("--listen-client-urls={client_urls}"),
format!("--advertise-client-urls={client_urls}"),
// Set --quota-backend-bytes to keep the etcd virtual memory
// size smaller. Our test etcd clusters are very small.
// See https://github.com/etcd-io/etcd/issues/7910
"--quota-backend-bytes=100000000".to_string(),
])
.stdout(Stdio::from(etcd_stdout_file))
.stderr(Stdio::from(etcd_stderr_file))
.spawn()
.context("Failed to spawn etcd subprocess")?;
let pid = etcd_process.id();
let etcd_pid_file_path = etcd_pid_file_path(env);
fs::write(&etcd_pid_file_path, pid.to_string()).with_context(|| {
format!(
"Failed to create etcd pid file at {}",
etcd_pid_file_path.display()
)
})?;
Ok(())
}
pub fn stop_etcd_process(env: &local_env::LocalEnv) -> anyhow::Result<()> {
let etcd_path = &env.etcd_broker.etcd_binary_path;
println!("Stopping etcd broker at {}", etcd_path.display());
let etcd_pid_file_path = etcd_pid_file_path(env);
let pid = Pid::from_raw(read_pidfile(&etcd_pid_file_path).with_context(|| {
format!(
"Failed to read etcd pid file at {}",
etcd_pid_file_path.display()
)
})?);
kill(pid, Signal::SIGTERM).with_context(|| {
format!(
"Failed to stop etcd with pid {pid} at {}",
etcd_pid_file_path.display()
)
})?;
Ok(())
}
fn etcd_pid_file_path(env: &local_env::LocalEnv) -> PathBuf {
env.base_data_dir.join("etcd.pid")
}

View File

@@ -6,11 +6,59 @@
// Intended to be used in integration tests and in CLI tools for
// local installations.
//
use anyhow::{anyhow, bail, Context, Result};
use std::fs;
use std::path::Path;
use std::process::Command;
mod background_process;
pub mod broker;
pub mod compute;
pub mod etcd;
pub mod local_env;
pub mod pageserver;
pub mod postgresql_conf;
pub mod safekeeper;
pub mod storage;
/// Read a PID file
///
/// We expect a file that contains a single integer.
/// We return an i32 for compatibility with libc and nix.
pub fn read_pidfile(pidfile: &Path) -> Result<i32> {
let pid_str = fs::read_to_string(pidfile)
.with_context(|| format!("failed to read pidfile {:?}", pidfile))?;
let pid: i32 = pid_str
.parse()
.map_err(|_| anyhow!("failed to parse pidfile {:?}", pidfile))?;
if pid < 1 {
bail!("pidfile {:?} contained bad value '{}'", pidfile, pid);
}
Ok(pid)
}
fn fill_rust_env_vars(cmd: &mut Command) -> &mut Command {
let cmd = cmd.env_clear().env("RUST_BACKTRACE", "1");
let var = "LLVM_PROFILE_FILE";
if let Some(val) = std::env::var_os(var) {
cmd.env(var, val);
}
const RUST_LOG_KEY: &str = "RUST_LOG";
if let Ok(rust_log_value) = std::env::var(RUST_LOG_KEY) {
cmd.env(RUST_LOG_KEY, rust_log_value)
} else {
cmd
}
}
fn fill_aws_secrets_vars(mut cmd: &mut Command) -> &mut Command {
for env_key in [
"AWS_ACCESS_KEY_ID",
"AWS_SECRET_ACCESS_KEY",
"AWS_SESSION_TOKEN",
] {
if let Ok(value) = std::env::var(env_key) {
cmd = cmd.env(env_key, value);
}
}
cmd
}

View File

@@ -4,28 +4,22 @@
//! script which will use local paths.
use anyhow::{bail, ensure, Context};
use reqwest::Url;
use serde::{Deserialize, Serialize};
use serde_with::{serde_as, DisplayFromStr};
use std::collections::HashMap;
use std::env;
use std::fs;
use std::net::IpAddr;
use std::net::Ipv4Addr;
use std::net::SocketAddr;
use std::path::{Path, PathBuf};
use std::process::{Command, Stdio};
use utils::{
auth::{encode_from_key_file, Claims, Scope},
id::{NodeId, TenantId, TenantTimelineId, TimelineId},
postgres_backend::AuthType,
zid::{NodeId, ZTenantId, ZTenantTimelineId, ZTimelineId},
};
use crate::safekeeper::SafekeeperNode;
pub const DEFAULT_PG_VERSION: u32 = 14;
//
// This data structures represents neon_local CLI config
//
@@ -54,19 +48,19 @@ pub struct LocalEnv {
// Path to pageserver binary.
#[serde(default)]
pub neon_distrib_dir: PathBuf,
pub zenith_distrib_dir: PathBuf,
// Default tenant ID to use with the 'neon_local' command line utility, when
// --tenant_id is not explicitly specified.
// Default tenant ID to use with the 'zenith' command line utility, when
// --tenantid is not explicitly specified.
#[serde(default)]
#[serde_as(as = "Option<DisplayFromStr>")]
pub default_tenant_id: Option<TenantId>,
pub default_tenant_id: Option<ZTenantId>,
// used to issue tokens during e.g pg start
#[serde(default)]
pub private_key_path: PathBuf,
pub broker: NeonBroker,
pub etcd_broker: EtcdBroker,
pub pageserver: PageServerConf,
@@ -75,33 +69,74 @@ pub struct LocalEnv {
/// Keep human-readable aliases in memory (and persist them to config), to hide ZId hex strings from the user.
#[serde(default)]
// A `HashMap<String, HashMap<TenantId, TimelineId>>` would be more appropriate here,
// A `HashMap<String, HashMap<ZTenantId, ZTimelineId>>` would be more appropriate here,
// but deserialization into a generic toml object as `toml::Value::try_from` fails with an error.
// https://toml.io/en/v1.0.0 does not contain a concept of "a table inside another table".
#[serde_as(as = "HashMap<_, Vec<(DisplayFromStr, DisplayFromStr)>>")]
branch_name_mappings: HashMap<String, Vec<(TenantId, TimelineId)>>,
branch_name_mappings: HashMap<String, Vec<(ZTenantId, ZTimelineId)>>,
}
/// Broker config for cluster internal communication.
/// Etcd broker config for cluster internal communication.
#[serde_as]
#[derive(Serialize, Deserialize, PartialEq, Eq, Clone, Debug)]
#[serde(default)]
pub struct NeonBroker {
/// Broker listen address for storage nodes coordination, e.g. '127.0.0.1:50051'.
pub listen_addr: SocketAddr,
pub struct EtcdBroker {
/// A prefix to all to any key when pushing/polling etcd from a node.
#[serde(default)]
pub broker_etcd_prefix: Option<String>,
/// Broker (etcd) endpoints for storage nodes coordination, e.g. 'http://127.0.0.1:2379'.
#[serde(default)]
#[serde_as(as = "Vec<DisplayFromStr>")]
pub broker_endpoints: Vec<Url>,
/// Etcd binary path to use.
#[serde(default)]
pub etcd_binary_path: PathBuf,
}
// Dummy Default impl to satisfy Deserialize derive.
impl Default for NeonBroker {
fn default() -> Self {
NeonBroker {
listen_addr: SocketAddr::new(IpAddr::V4(Ipv4Addr::new(0, 0, 0, 0)), 0),
}
impl EtcdBroker {
pub fn locate_etcd() -> anyhow::Result<PathBuf> {
let which_output = Command::new("which")
.arg("etcd")
.output()
.context("Failed to run 'which etcd' command")?;
let stdout = String::from_utf8_lossy(&which_output.stdout);
ensure!(
which_output.status.success(),
"'which etcd' invocation failed. Status: {}, stdout: {stdout}, stderr: {}",
which_output.status,
String::from_utf8_lossy(&which_output.stderr)
);
let etcd_path = PathBuf::from(stdout.trim());
ensure!(
etcd_path.is_file(),
"'which etcd' invocation was successful, but the path it returned is not a file or does not exist: {}",
etcd_path.display()
);
Ok(etcd_path)
}
}
impl NeonBroker {
pub fn client_url(&self) -> Url {
Url::parse(&format!("http://{}", self.listen_addr)).expect("failed to construct url")
pub fn comma_separated_endpoints(&self) -> String {
self.broker_endpoints
.iter()
.map(|url| {
// URL by default adds a '/' path at the end, which is not what etcd CLI wants.
let url_string = url.as_str();
if url_string.ends_with('/') {
&url_string[0..url_string.len() - 1]
} else {
url_string
}
})
.fold(String::new(), |mut comma_separated_urls, url| {
if !comma_separated_urls.is_empty() {
comma_separated_urls.push(',');
}
comma_separated_urls.push_str(url);
comma_separated_urls
})
}
}
@@ -160,54 +195,29 @@ impl Default for SafekeeperConf {
}
impl LocalEnv {
pub fn pg_distrib_dir_raw(&self) -> PathBuf {
self.pg_distrib_dir.clone()
// postgres installation paths
pub fn pg_bin_dir(&self) -> PathBuf {
self.pg_distrib_dir.join("bin")
}
pub fn pg_lib_dir(&self) -> PathBuf {
self.pg_distrib_dir.join("lib")
}
pub fn pg_distrib_dir(&self, pg_version: u32) -> anyhow::Result<PathBuf> {
let path = self.pg_distrib_dir.clone();
match pg_version {
14 => Ok(path.join(format!("v{pg_version}"))),
15 => Ok(path.join(format!("v{pg_version}"))),
_ => bail!("Unsupported postgres version: {}", pg_version),
}
pub fn pageserver_bin(&self) -> anyhow::Result<PathBuf> {
Ok(self.zenith_distrib_dir.join("pageserver"))
}
pub fn pg_bin_dir(&self, pg_version: u32) -> anyhow::Result<PathBuf> {
match pg_version {
14 => Ok(self.pg_distrib_dir(pg_version)?.join("bin")),
15 => Ok(self.pg_distrib_dir(pg_version)?.join("bin")),
_ => bail!("Unsupported postgres version: {}", pg_version),
}
}
pub fn pg_lib_dir(&self, pg_version: u32) -> anyhow::Result<PathBuf> {
match pg_version {
14 => Ok(self.pg_distrib_dir(pg_version)?.join("lib")),
15 => Ok(self.pg_distrib_dir(pg_version)?.join("lib")),
_ => bail!("Unsupported postgres version: {}", pg_version),
}
}
pub fn pageserver_bin(&self) -> PathBuf {
self.neon_distrib_dir.join("pageserver")
}
pub fn safekeeper_bin(&self) -> PathBuf {
self.neon_distrib_dir.join("safekeeper")
}
pub fn storage_broker_bin(&self) -> PathBuf {
self.neon_distrib_dir.join("storage_broker")
pub fn safekeeper_bin(&self) -> anyhow::Result<PathBuf> {
Ok(self.zenith_distrib_dir.join("safekeeper"))
}
pub fn pg_data_dirs_path(&self) -> PathBuf {
self.base_data_dir.join("pgdatadirs").join("tenants")
}
pub fn pg_data_dir(&self, tenant_id: &TenantId, branch_name: &str) -> PathBuf {
pub fn pg_data_dir(&self, tenantid: &ZTenantId, branch_name: &str) -> PathBuf {
self.pg_data_dirs_path()
.join(tenant_id.to_string())
.join(tenantid.to_string())
.join(branch_name)
}
@@ -223,8 +233,8 @@ impl LocalEnv {
pub fn register_branch_mapping(
&mut self,
branch_name: String,
tenant_id: TenantId,
timeline_id: TimelineId,
tenant_id: ZTenantId,
timeline_id: ZTimelineId,
) -> anyhow::Result<()> {
let existing_values = self
.branch_name_mappings
@@ -250,22 +260,22 @@ impl LocalEnv {
pub fn get_branch_timeline_id(
&self,
branch_name: &str,
tenant_id: TenantId,
) -> Option<TimelineId> {
tenant_id: ZTenantId,
) -> Option<ZTimelineId> {
self.branch_name_mappings
.get(branch_name)?
.iter()
.find(|(mapped_tenant_id, _)| mapped_tenant_id == &tenant_id)
.map(|&(_, timeline_id)| timeline_id)
.map(TimelineId::from)
.map(ZTimelineId::from)
}
pub fn timeline_name_mappings(&self) -> HashMap<TenantTimelineId, String> {
pub fn timeline_name_mappings(&self) -> HashMap<ZTenantTimelineId, String> {
self.branch_name_mappings
.iter()
.flat_map(|(name, tenant_timelines)| {
tenant_timelines.iter().map(|&(tenant_id, timeline_id)| {
(TenantTimelineId::new(tenant_id, timeline_id), name.clone())
(ZTenantTimelineId::new(tenant_id, timeline_id), name.clone())
})
})
.collect()
@@ -279,26 +289,24 @@ impl LocalEnv {
let mut env: LocalEnv = toml::from_str(toml)?;
// Find postgres binaries.
// Follow POSTGRES_DISTRIB_DIR if set, otherwise look in "pg_install".
// Note that later in the code we assume, that distrib dirs follow the same pattern
// for all postgres versions.
// Follow POSTGRES_DISTRIB_DIR if set, otherwise look in "tmp_install".
if env.pg_distrib_dir == Path::new("") {
if let Some(postgres_bin) = env::var_os("POSTGRES_DISTRIB_DIR") {
env.pg_distrib_dir = postgres_bin.into();
} else {
let cwd = env::current_dir()?;
env.pg_distrib_dir = cwd.join("pg_install")
env.pg_distrib_dir = cwd.join("tmp_install")
}
}
// Find neon binaries.
if env.neon_distrib_dir == Path::new("") {
env.neon_distrib_dir = env::current_exe()?.parent().unwrap().to_owned();
// Find zenith binaries.
if env.zenith_distrib_dir == Path::new("") {
env.zenith_distrib_dir = env::current_exe()?.parent().unwrap().to_owned();
}
// If no initial tenant ID was given, generate it.
if env.default_tenant_id.is_none() {
env.default_tenant_id = Some(TenantId::generate());
env.default_tenant_id = Some(ZTenantId::generate());
}
env.base_data_dir = base_path();
@@ -312,12 +320,12 @@ impl LocalEnv {
if !repopath.exists() {
bail!(
"Neon config is not found in {}. You need to run 'neon_local init' first",
"Zenith config is not found in {}. You need to run 'neon_local init' first",
repopath.to_str().unwrap()
);
}
// TODO: check that it looks like a neon repository
// TODO: check that it looks like a zenith repository
// load and parse file
let config = fs::read_to_string(repopath.join("config"))?;
@@ -376,7 +384,7 @@ impl LocalEnv {
//
// Initialize a new Neon repository
//
pub fn init(&mut self, pg_version: u32) -> anyhow::Result<()> {
pub fn init(&mut self) -> anyhow::Result<()> {
// check if config already exists
let base_path = &self.base_data_dir;
ensure!(
@@ -389,22 +397,22 @@ impl LocalEnv {
"directory '{}' already exists. Perhaps already initialized?",
base_path.display()
);
if !self.pg_bin_dir(pg_version)?.join("postgres").exists() {
if !self.pg_distrib_dir.join("bin/postgres").exists() {
bail!(
"Can't find postgres binary at {}",
self.pg_bin_dir(pg_version)?.display()
self.pg_distrib_dir.display()
);
}
for binary in ["pageserver", "safekeeper"] {
if !self.neon_distrib_dir.join(binary).exists() {
if !self.zenith_distrib_dir.join(binary).exists() {
bail!(
"Can't find binary '{binary}' in neon distrib dir '{}'",
self.neon_distrib_dir.display()
"Can't find binary '{binary}' in zenith distrib dir '{}'",
self.zenith_distrib_dir.display()
);
}
}
fs::create_dir(base_path)?;
fs::create_dir(&base_path)?;
// generate keys for jwt
// openssl genrsa -out private_key.pem 2048
@@ -413,7 +421,7 @@ impl LocalEnv {
private_key_path = base_path.join("auth_private_key.pem");
let keygen_output = Command::new("openssl")
.arg("genrsa")
.args(["-out", private_key_path.to_str().unwrap()])
.args(&["-out", private_key_path.to_str().unwrap()])
.arg("2048")
.stdout(Stdio::null())
.output()
@@ -430,10 +438,10 @@ impl LocalEnv {
// openssl rsa -in private_key.pem -pubout -outform PEM -out public_key.pem
let keygen_output = Command::new("openssl")
.arg("rsa")
.args(["-in", private_key_path.to_str().unwrap()])
.args(&["-in", private_key_path.to_str().unwrap()])
.arg("-pubout")
.args(["-outform", "PEM"])
.args(["-out", public_key_path.to_str().unwrap()])
.args(&["-outform", "PEM"])
.args(&["-out", public_key_path.to_str().unwrap()])
.stdout(Stdio::null())
.output()
.context("failed to generate auth private key")?;
@@ -478,8 +486,8 @@ mod tests {
"failed to parse simple config {simple_conf_toml}, reason: {simple_conf_parse_result:?}"
);
let string_to_replace = "listen_addr = '127.0.0.1:50051'";
let spoiled_url_str = "listen_addr = '!@$XOXO%^&'";
let string_to_replace = "broker_endpoints = ['http://127.0.0.1:2379']";
let spoiled_url_str = "broker_endpoints = ['!@$XOXO%^&']";
let spoiled_url_toml = simple_conf_toml.replace(string_to_replace, spoiled_url_str);
assert!(
spoiled_url_toml.contains(spoiled_url_str),

View File

@@ -1,592 +0,0 @@
use std::borrow::Cow;
use std::collections::HashMap;
use std::fs::File;
use std::io::{BufReader, Write};
use std::num::NonZeroU64;
use std::path::PathBuf;
use std::process::{Child, Command};
use std::{io, result};
use anyhow::{bail, ensure, Context};
use pageserver_api::models::{
TenantConfigRequest, TenantCreateRequest, TenantInfo, TimelineCreateRequest, TimelineInfo,
};
use postgres_connection::{parse_host_port, PgConnectionConfig};
use reqwest::blocking::{Client, RequestBuilder, Response};
use reqwest::{IntoUrl, Method};
use thiserror::Error;
use utils::auth::{Claims, Scope};
use utils::{
http::error::HttpErrorBody,
id::{TenantId, TimelineId},
lsn::Lsn,
postgres_backend::AuthType,
};
use crate::{background_process, local_env::LocalEnv};
#[derive(Error, Debug)]
pub enum PageserverHttpError {
#[error("Reqwest error: {0}")]
Transport(#[from] reqwest::Error),
#[error("Error: {0}")]
Response(String),
}
impl From<anyhow::Error> for PageserverHttpError {
fn from(e: anyhow::Error) -> Self {
Self::Response(e.to_string())
}
}
type Result<T> = result::Result<T, PageserverHttpError>;
pub trait ResponseErrorMessageExt: Sized {
fn error_from_body(self) -> Result<Self>;
}
impl ResponseErrorMessageExt for Response {
fn error_from_body(self) -> Result<Self> {
let status = self.status();
if !(status.is_client_error() || status.is_server_error()) {
return Ok(self);
}
// reqwest does not export its error construction utility functions, so let's craft the message ourselves
let url = self.url().to_owned();
Err(PageserverHttpError::Response(
match self.json::<HttpErrorBody>() {
Ok(err_body) => format!("Error: {}", err_body.msg),
Err(_) => format!("Http error ({}) at {}.", status.as_u16(), url),
},
))
}
}
//
// Control routines for pageserver.
//
// Used in CLI and tests.
//
#[derive(Debug)]
pub struct PageServerNode {
pub pg_connection_config: PgConnectionConfig,
pub env: LocalEnv,
pub http_client: Client,
pub http_base_url: String,
}
impl PageServerNode {
pub fn from_env(env: &LocalEnv) -> PageServerNode {
let (host, port) = parse_host_port(&env.pageserver.listen_pg_addr)
.expect("Unable to parse listen_pg_addr");
let port = port.unwrap_or(5432);
let password = if env.pageserver.auth_type == AuthType::NeonJWT {
Some(env.pageserver.auth_token.clone())
} else {
None
};
Self {
pg_connection_config: PgConnectionConfig::new_host_port(host, port)
.set_password(password),
env: env.clone(),
http_client: Client::new(),
http_base_url: format!("http://{}/v1", env.pageserver.listen_http_addr),
}
}
// pageserver conf overrides defined by neon_local configuration.
fn neon_local_overrides(&self) -> Vec<String> {
let id = format!("id={}", self.env.pageserver.id);
// FIXME: the paths should be shell-escaped to handle paths with spaces, quotas etc.
let pg_distrib_dir_param = format!(
"pg_distrib_dir='{}'",
self.env.pg_distrib_dir_raw().display()
);
let authg_type_param = format!("auth_type='{}'", self.env.pageserver.auth_type);
let listen_http_addr_param = format!(
"listen_http_addr='{}'",
self.env.pageserver.listen_http_addr
);
let listen_pg_addr_param =
format!("listen_pg_addr='{}'", self.env.pageserver.listen_pg_addr);
let broker_endpoint_param = format!("broker_endpoint='{}'", self.env.broker.client_url());
let mut overrides = vec![
id,
pg_distrib_dir_param,
authg_type_param,
listen_http_addr_param,
listen_pg_addr_param,
broker_endpoint_param,
];
if self.env.pageserver.auth_type != AuthType::Trust {
overrides.push("auth_validation_public_key_path='auth_public_key.pem'".to_owned());
}
overrides
}
/// Initializes a pageserver node by creating its config with the overrides provided,
/// and creating an initial tenant and timeline afterwards.
pub fn initialize(
&self,
create_tenant: Option<TenantId>,
initial_timeline_id: Option<TimelineId>,
config_overrides: &[&str],
pg_version: u32,
) -> anyhow::Result<TimelineId> {
// First, run `pageserver --init` and wait for it to write a config into FS and exit.
self.pageserver_init(config_overrides).with_context(|| {
format!(
"Failed to run init for pageserver node {}",
self.env.pageserver.id,
)
})?;
// Then, briefly start it fully to run HTTP commands on it,
// to create initial tenant and timeline.
// We disable the remote storage, since we stop pageserver right after the timeline creation,
// hence most of the uploads will either aborted or not started: no point to start them at all.
let disabled_remote_storage_override = "remote_storage={}";
let mut pageserver_process = self
.start_node(
&[disabled_remote_storage_override],
// Previous overrides will be taken from the config created before, don't overwrite them.
false,
)
.with_context(|| {
format!(
"Failed to start a process for pageserver node {}",
self.env.pageserver.id,
)
})?;
let init_result = self
.try_init_timeline(create_tenant, initial_timeline_id, pg_version)
.context("Failed to create initial tenant and timeline for pageserver");
match &init_result {
Ok(initial_timeline_id) => {
println!("Successfully initialized timeline {initial_timeline_id}")
}
Err(e) => eprintln!("{e:#}"),
}
background_process::send_stop_child_process(&pageserver_process)?;
let exit_code = pageserver_process.wait()?;
ensure!(
exit_code.success(),
format!(
"pageserver init failed with exit code {:?}",
exit_code.code()
)
);
println!(
"Stopped pageserver {} process with pid {}",
self.env.pageserver.id,
pageserver_process.id(),
);
init_result
}
fn try_init_timeline(
&self,
new_tenant_id: Option<TenantId>,
new_timeline_id: Option<TimelineId>,
pg_version: u32,
) -> anyhow::Result<TimelineId> {
let initial_tenant_id = self.tenant_create(new_tenant_id, HashMap::new())?;
let initial_timeline_info = self.timeline_create(
initial_tenant_id,
new_timeline_id,
None,
None,
Some(pg_version),
)?;
Ok(initial_timeline_info.timeline_id)
}
pub fn repo_path(&self) -> PathBuf {
self.env.pageserver_data_dir()
}
/// The pid file is created by the pageserver process, with its pid stored inside.
/// Other pageservers cannot lock the same file and overwrite it for as long as the current
/// pageserver runs. (Unless someone removes the file manually; never do that!)
fn pid_file(&self) -> PathBuf {
self.repo_path().join("pageserver.pid")
}
pub fn start(&self, config_overrides: &[&str]) -> anyhow::Result<Child> {
self.start_node(config_overrides, false)
}
fn pageserver_init(&self, config_overrides: &[&str]) -> anyhow::Result<()> {
let datadir = self.repo_path();
let node_id = self.env.pageserver.id;
println!(
"Initializing pageserver node {} at '{}' in {:?}",
node_id,
self.pg_connection_config.raw_address(),
datadir
);
io::stdout().flush()?;
let datadir_path_str = datadir.to_str().with_context(|| {
format!("Cannot start pageserver node {node_id} in path that has no string representation: {datadir:?}")
})?;
let mut args = self.pageserver_basic_args(config_overrides, datadir_path_str);
args.push(Cow::Borrowed("--init"));
let init_output = Command::new(self.env.pageserver_bin())
.args(args.iter().map(Cow::as_ref))
.envs(self.pageserver_env_variables()?)
.output()
.with_context(|| format!("Failed to run pageserver init for node {node_id}"))?;
anyhow::ensure!(
init_output.status.success(),
"Pageserver init for node {} did not finish successfully, stdout: {}, stderr: {}",
node_id,
String::from_utf8_lossy(&init_output.stdout),
String::from_utf8_lossy(&init_output.stderr),
);
Ok(())
}
fn start_node(&self, config_overrides: &[&str], update_config: bool) -> anyhow::Result<Child> {
let mut overrides = self.neon_local_overrides();
overrides.extend(config_overrides.iter().map(|&c| c.to_owned()));
let datadir = self.repo_path();
print!(
"Starting pageserver node {} at '{}' in {:?}",
self.env.pageserver.id,
self.pg_connection_config.raw_address(),
datadir
);
io::stdout().flush()?;
let datadir_path_str = datadir.to_str().with_context(|| {
format!(
"Cannot start pageserver node {} in path that has no string representation: {:?}",
self.env.pageserver.id, datadir,
)
})?;
let mut args = self.pageserver_basic_args(config_overrides, datadir_path_str);
if update_config {
args.push(Cow::Borrowed("--update-config"));
}
background_process::start_process(
"pageserver",
&datadir,
&self.env.pageserver_bin(),
args.iter().map(Cow::as_ref),
self.pageserver_env_variables()?,
background_process::InitialPidFile::Expect(&self.pid_file()),
|| match self.check_status() {
Ok(()) => Ok(true),
Err(PageserverHttpError::Transport(_)) => Ok(false),
Err(e) => Err(anyhow::anyhow!("Failed to check node status: {e}")),
},
)
}
fn pageserver_basic_args<'a>(
&self,
config_overrides: &'a [&'a str],
datadir_path_str: &'a str,
) -> Vec<Cow<'a, str>> {
let mut args = vec![Cow::Borrowed("-D"), Cow::Borrowed(datadir_path_str)];
let mut overrides = self.neon_local_overrides();
overrides.extend(config_overrides.iter().map(|&c| c.to_owned()));
for config_override in overrides {
args.push(Cow::Borrowed("-c"));
args.push(Cow::Owned(config_override));
}
args
}
fn pageserver_env_variables(&self) -> anyhow::Result<Vec<(String, String)>> {
Ok(if self.env.pageserver.auth_type != AuthType::Trust {
// Generate a token to connect from the pageserver to a safekeeper
let token = self
.env
.generate_auth_token(&Claims::new(None, Scope::SafekeeperData))?;
vec![("NEON_AUTH_TOKEN".to_owned(), token)]
} else {
Vec::new()
})
}
///
/// Stop the server.
///
/// If 'immediate' is true, we use SIGQUIT, killing the process immediately.
/// Otherwise we use SIGTERM, triggering a clean shutdown
///
/// If the server is not running, returns success
///
pub fn stop(&self, immediate: bool) -> anyhow::Result<()> {
background_process::stop_process(immediate, "pageserver", &self.pid_file())
}
pub fn page_server_psql(&self, sql: &str) -> Vec<postgres::SimpleQueryMessage> {
let mut client = self.pg_connection_config.connect_no_tls().unwrap();
println!("Pageserver query: '{sql}'");
client.simple_query(sql).unwrap()
}
pub fn page_server_psql_client(&self) -> result::Result<postgres::Client, postgres::Error> {
self.pg_connection_config.connect_no_tls()
}
fn http_request<U: IntoUrl>(&self, method: Method, url: U) -> RequestBuilder {
let mut builder = self.http_client.request(method, url);
if self.env.pageserver.auth_type == AuthType::NeonJWT {
builder = builder.bearer_auth(&self.env.pageserver.auth_token)
}
builder
}
pub fn check_status(&self) -> Result<()> {
self.http_request(Method::GET, format!("{}/status", self.http_base_url))
.send()?
.error_from_body()?;
Ok(())
}
pub fn tenant_list(&self) -> Result<Vec<TenantInfo>> {
Ok(self
.http_request(Method::GET, format!("{}/tenant", self.http_base_url))
.send()?
.error_from_body()?
.json()?)
}
pub fn tenant_create(
&self,
new_tenant_id: Option<TenantId>,
settings: HashMap<&str, &str>,
) -> anyhow::Result<TenantId> {
let mut settings = settings.clone();
let request = TenantCreateRequest {
new_tenant_id,
checkpoint_distance: settings
.remove("checkpoint_distance")
.map(|x| x.parse::<u64>())
.transpose()?,
checkpoint_timeout: settings.remove("checkpoint_timeout").map(|x| x.to_string()),
compaction_target_size: settings
.remove("compaction_target_size")
.map(|x| x.parse::<u64>())
.transpose()?,
compaction_period: settings.remove("compaction_period").map(|x| x.to_string()),
compaction_threshold: settings
.remove("compaction_threshold")
.map(|x| x.parse::<usize>())
.transpose()?,
gc_horizon: settings
.remove("gc_horizon")
.map(|x| x.parse::<u64>())
.transpose()?,
gc_period: settings.remove("gc_period").map(|x| x.to_string()),
image_creation_threshold: settings
.remove("image_creation_threshold")
.map(|x| x.parse::<usize>())
.transpose()?,
pitr_interval: settings.remove("pitr_interval").map(|x| x.to_string()),
walreceiver_connect_timeout: settings
.remove("walreceiver_connect_timeout")
.map(|x| x.to_string()),
lagging_wal_timeout: settings
.remove("lagging_wal_timeout")
.map(|x| x.to_string()),
max_lsn_wal_lag: settings
.remove("max_lsn_wal_lag")
.map(|x| x.parse::<NonZeroU64>())
.transpose()
.context("Failed to parse 'max_lsn_wal_lag' as non zero integer")?,
trace_read_requests: settings
.remove("trace_read_requests")
.map(|x| x.parse::<bool>())
.transpose()
.context("Failed to parse 'trace_read_requests' as bool")?,
};
if !settings.is_empty() {
bail!("Unrecognized tenant settings: {settings:?}")
}
self.http_request(Method::POST, format!("{}/tenant", self.http_base_url))
.json(&request)
.send()?
.error_from_body()?
.json::<Option<String>>()
.with_context(|| {
format!("Failed to parse tenant creation response for tenant id: {new_tenant_id:?}")
})?
.context("No tenant id was found in the tenant creation response")
.and_then(|tenant_id_string| {
tenant_id_string.parse().with_context(|| {
format!("Failed to parse response string as tenant id: '{tenant_id_string}'")
})
})
}
pub fn tenant_config(&self, tenant_id: TenantId, settings: HashMap<&str, &str>) -> Result<()> {
self.http_request(Method::PUT, format!("{}/tenant/config", self.http_base_url))
.json(&TenantConfigRequest {
tenant_id,
checkpoint_distance: settings
.get("checkpoint_distance")
.map(|x| x.parse::<u64>())
.transpose()
.context("Failed to parse 'checkpoint_distance' as an integer")?,
checkpoint_timeout: settings.get("checkpoint_timeout").map(|x| x.to_string()),
compaction_target_size: settings
.get("compaction_target_size")
.map(|x| x.parse::<u64>())
.transpose()
.context("Failed to parse 'compaction_target_size' as an integer")?,
compaction_period: settings.get("compaction_period").map(|x| x.to_string()),
compaction_threshold: settings
.get("compaction_threshold")
.map(|x| x.parse::<usize>())
.transpose()
.context("Failed to parse 'compaction_threshold' as an integer")?,
gc_horizon: settings
.get("gc_horizon")
.map(|x| x.parse::<u64>())
.transpose()
.context("Failed to parse 'gc_horizon' as an integer")?,
gc_period: settings.get("gc_period").map(|x| x.to_string()),
image_creation_threshold: settings
.get("image_creation_threshold")
.map(|x| x.parse::<usize>())
.transpose()
.context("Failed to parse 'image_creation_threshold' as non zero integer")?,
pitr_interval: settings.get("pitr_interval").map(|x| x.to_string()),
walreceiver_connect_timeout: settings
.get("walreceiver_connect_timeout")
.map(|x| x.to_string()),
lagging_wal_timeout: settings.get("lagging_wal_timeout").map(|x| x.to_string()),
max_lsn_wal_lag: settings
.get("max_lsn_wal_lag")
.map(|x| x.parse::<NonZeroU64>())
.transpose()
.context("Failed to parse 'max_lsn_wal_lag' as non zero integer")?,
trace_read_requests: settings
.get("trace_read_requests")
.map(|x| x.parse::<bool>())
.transpose()
.context("Failed to parse 'trace_read_requests' as bool")?,
})
.send()?
.error_from_body()?;
Ok(())
}
pub fn timeline_list(&self, tenant_id: &TenantId) -> anyhow::Result<Vec<TimelineInfo>> {
let timeline_infos: Vec<TimelineInfo> = self
.http_request(
Method::GET,
format!("{}/tenant/{}/timeline", self.http_base_url, tenant_id),
)
.send()?
.error_from_body()?
.json()?;
Ok(timeline_infos)
}
pub fn timeline_create(
&self,
tenant_id: TenantId,
new_timeline_id: Option<TimelineId>,
ancestor_start_lsn: Option<Lsn>,
ancestor_timeline_id: Option<TimelineId>,
pg_version: Option<u32>,
) -> anyhow::Result<TimelineInfo> {
self.http_request(
Method::POST,
format!("{}/tenant/{}/timeline", self.http_base_url, tenant_id),
)
.json(&TimelineCreateRequest {
new_timeline_id,
ancestor_start_lsn,
ancestor_timeline_id,
pg_version,
})
.send()?
.error_from_body()?
.json::<Option<TimelineInfo>>()
.with_context(|| {
format!("Failed to parse timeline creation response for tenant id: {tenant_id}")
})?
.with_context(|| {
format!(
"No timeline id was found in the timeline creation response for tenant {tenant_id}"
)
})
}
/// Import a basebackup prepared using either:
/// a) `pg_basebackup -F tar`, or
/// b) The `fullbackup` pageserver endpoint
///
/// # Arguments
/// * `tenant_id` - tenant to import into. Created if not exists
/// * `timeline_id` - id to assign to imported timeline
/// * `base` - (start lsn of basebackup, path to `base.tar` file)
/// * `pg_wal` - if there's any wal to import: (end lsn, path to `pg_wal.tar`)
pub fn timeline_import(
&self,
tenant_id: TenantId,
timeline_id: TimelineId,
base: (Lsn, PathBuf),
pg_wal: Option<(Lsn, PathBuf)>,
pg_version: u32,
) -> anyhow::Result<()> {
let mut client = self.pg_connection_config.connect_no_tls().unwrap();
// Init base reader
let (start_lsn, base_tarfile_path) = base;
let base_tarfile = File::open(base_tarfile_path)?;
let mut base_reader = BufReader::new(base_tarfile);
// Init wal reader if necessary
let (end_lsn, wal_reader) = if let Some((end_lsn, wal_tarfile_path)) = pg_wal {
let wal_tarfile = File::open(wal_tarfile_path)?;
let wal_reader = BufReader::new(wal_tarfile);
(end_lsn, Some(wal_reader))
} else {
(start_lsn, None)
};
// Import base
let import_cmd = format!(
"import basebackup {tenant_id} {timeline_id} {start_lsn} {end_lsn} {pg_version}"
);
let mut writer = client.copy_in(&import_cmd)?;
io::copy(&mut base_reader, &mut writer)?;
writer.finish()?;
// Import wal if necessary
if let Some(mut wal_reader) = wal_reader {
let import_cmd = format!("import wal {tenant_id} {timeline_id} {start_lsn} {end_lsn}");
let mut writer = client.copy_in(&import_cmd)?;
io::copy(&mut wal_reader, &mut writer)?;
writer.finish()?;
}
Ok(())
}
}

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