Compare commits

..

1 Commits

Author SHA1 Message Date
Heikki Linnakangas
6862a803b1 Cache initdb output to speed up tenant creation in tests
initdb takes about 1 s. Our tests create and destroy a lot of tenants,
so that adds up. Cache the initdb result to speed it up.

This is currently only enabled in tests. Out of caution, mostly. But
also because when you reuse the initdb result, all the postgres
clusters end up having the same system_identifier, which is supposed
to be unique. It's not necessary for it to be unique for correctness,
nothing critical relies on it and you can easily end up with duplicate
system_identifiers in standalone PostgreSQL too, if you e.g. create a
backup and restore it on a different system. But it is used in various
checks to reduce the chance that you e.g. accidentally apply WAL
belonging to a different cluster.

Because this is aimed at tests, there are a few things that might be
surprising:

- The initdb cache directory is configurable, and can be outside the
  pageserver's repo directory. This allows reuse across different
  pageservers running on the same host. In production use, that'd be
  pointless, but our tests create a lot of pageservers.

- The cache is not automatically purged at start / shutdown. For
  production use, we'd probably want that, so that we'd pick up any
  changes in what an empty cluster looks like after a Postgres minor
  version upgrade, for example. But again tests create and destroy a
  lot of pageservers, so it's important to retain the cache.

- The locking on the cache directory relies purely on filesystem
  operations and atomic rename(). Using e.g. a rust Mutex() would be
  more straightforward, but that's not enough because the cache needs
  to be shared between different pageservers running on the same
  system.
2024-09-21 02:09:39 +03:00
1643 changed files with 58677 additions and 220731 deletions

View File

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

View File

@@ -21,20 +21,18 @@ platforms = [
# "x86_64-apple-darwin",
# "x86_64-pc-windows-msvc",
]
[final-excludes]
workspace-members = [
# vm_monitor benefits from the same Cargo.lock as the rest of our artifacts, but
# it is built primarly in separate repo neondatabase/autoscaling and thus is excluded
# from depending on workspace-hack because most of the dependencies are not used.
"vm_monitor",
# subzero-core is a stub crate that should be excluded from workspace-hack
"subzero-core",
# All of these exist in libs and are not usually built independently.
# Putting workspace hack there adds a bottleneck for cargo builds.
"compute_api",
"consumption_metrics",
"desim",
"json",
"metrics",
"pageserver_api",
"postgres_backend",
@@ -48,9 +46,6 @@ workspace-members = [
"utils",
"wal_craft",
"walproposer",
"postgres-protocol2",
"postgres-types2",
"tokio-postgres2",
]
# Write out exact versions rather than a semver range. (Defaults to false.)

View File

@@ -4,27 +4,27 @@
!Cargo.lock
!Cargo.toml
!Makefile
!postgres.mk
!rust-toolchain.toml
!scripts/combine_control_files.py
!scripts/ninstall.sh
!vm-cgconfig.conf
!docker-compose/run-tests.sh
# Directories
!.cargo/
!.config/
!compute/
!compute_tools/
!control_plane/
!docker-compose/ext-src
!libs/
!neon_local/
!pageserver/
!patches/
!pgxn/
!proxy/
!endpoint_storage/
!storage_scrubber/
!safekeeper/
!storage_broker/
!storage_controller/
!trace/
!vendor/postgres-*/
!workspace_hack/
!build-tools/patches

View File

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

View File

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

View File

@@ -0,0 +1,21 @@
## 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://www.notion.so/neondatabase/Release-general-flow-61f2e39fd45d4d14a70c7749604bd70b)
- [ ] 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
- [ ] Make sure instructions from PRs included in this release and labeled `manual_release_instructions` are executed (either by you or by people who wrote them).
- [ ] Based on the merged commits write release notes and open a PR into `website` repo ([example](https://github.com/neondatabase/website/pull/219/files))
- [ ] Check [#dev-production-stream](https://neondb.slack.com/archives/C03F5SM1N02) Slack channel
- [ ] Check [stuck projects page](https://console.neon.tech/admin/projects?sort=last_active&order=desc&stuck=true)
- [ ] 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

@@ -4,13 +4,9 @@ self-hosted-runner:
- large
- large-arm64
- small
- small-metal
- small-arm64
- unit-perf
- unit-perf-aws-arm
- us-east-2
config-variables:
- AWS_ECR_REGION
- AZURE_DEV_CLIENT_ID
- AZURE_DEV_REGISTRY_NAME
- AZURE_DEV_SUBSCRIPTION_ID
@@ -18,31 +14,9 @@ config-variables:
- AZURE_PROD_REGISTRY_NAME
- AZURE_PROD_SUBSCRIPTION_ID
- AZURE_TENANT_ID
- BENCHMARK_INGEST_TARGET_PROJECTID
- BENCHMARK_LARGE_OLTP_PROJECTID
- BENCHMARK_PROJECT_ID_PUB
- BENCHMARK_PROJECT_ID_SUB
- DEV_AWS_OIDC_ROLE_ARN
- DEV_AWS_OIDC_ROLE_MANAGE_BENCHMARK_EC2_VMS_ARN
- HETZNER_CACHE_BUCKET
- HETZNER_CACHE_ENDPOINT
- HETZNER_CACHE_REGION
- NEON_DEV_AWS_ACCOUNT_ID
- NEON_PROD_AWS_ACCOUNT_ID
- PGREGRESS_PG16_PROJECT_ID
- PGREGRESS_PG17_PROJECT_ID
- PREWARM_PGBENCH_SIZE
- REMOTE_STORAGE_AZURE_CONTAINER
- REMOTE_STORAGE_AZURE_REGION
- SLACK_CICD_CHANNEL_ID
- SLACK_COMPUTE_CHANNEL_ID
- SLACK_ON_CALL_DEVPROD_STREAM
- SLACK_ON_CALL_QA_STAGING_STREAM
- SLACK_ON_CALL_STORAGE_STAGING_STREAM
- SLACK_ONCALL_COMPUTE_GROUP
- SLACK_ONCALL_PROXY_GROUP
- SLACK_ONCALL_STORAGE_GROUP
- SLACK_PROXY_CHANNEL_ID
- SLACK_RUST_CHANNEL_ID
- SLACK_STORAGE_CHANNEL_ID
- SLACK_UPCOMING_RELEASE_CHANNEL_ID
- DEV_AWS_OIDC_ROLE_ARN

View File

@@ -7,9 +7,6 @@ inputs:
type: boolean
required: false
default: false
aws-oidc-role-arn:
description: 'OIDC role arn to interract with S3'
required: true
outputs:
base-url:
@@ -38,14 +35,11 @@ runs:
#
- name: Set variables
shell: bash -euxo pipefail {0}
env:
PR_NUMBER: ${{ github.event.pull_request.number }}
BUCKET: neon-github-public-dev
run: |
if [ -n "${PR_NUMBER}" ]; then
PR_NUMBER=$(jq --raw-output .pull_request.number "$GITHUB_EVENT_PATH" || true)
if [ "${PR_NUMBER}" != "null" ]; then
BRANCH_OR_PR=pr-${PR_NUMBER}
elif [ "${GITHUB_REF_NAME}" = "main" ] || [ "${GITHUB_REF_NAME}" = "release" ] || \
[ "${GITHUB_REF_NAME}" = "release-proxy" ] || [ "${GITHUB_REF_NAME}" = "release-compute" ]; then
elif [ "${GITHUB_REF_NAME}" = "main" ] || [ "${GITHUB_REF_NAME}" = "release" ] || [ "${GITHUB_REF_NAME}" = "release-proxy" ]; then
# Shortcut for special branches
BRANCH_OR_PR=${GITHUB_REF_NAME}
else
@@ -61,6 +55,8 @@ runs:
echo "LOCK_FILE=${LOCK_FILE}" >> $GITHUB_ENV
echo "WORKDIR=${WORKDIR}" >> $GITHUB_ENV
echo "BUCKET=${BUCKET}" >> $GITHUB_ENV
env:
BUCKET: neon-github-public-dev
# TODO: We can replace with a special docker image with Java and Allure pre-installed
- uses: actions/setup-java@v4
@@ -70,7 +66,6 @@ runs:
- name: Install Allure
shell: bash -euxo pipefail {0}
working-directory: /tmp
run: |
if ! which allure; then
ALLURE_ZIP=allure-${ALLURE_VERSION}.zip
@@ -81,15 +76,8 @@ runs:
rm -f ${ALLURE_ZIP}
fi
env:
ALLURE_VERSION: 2.32.2
ALLURE_ZIP_SHA256: 3f28885e2118f6317c92f667eaddcc6491400af1fb9773c1f3797a5fa5174953
- uses: aws-actions/configure-aws-credentials@v4
if: ${{ !cancelled() }}
with:
aws-region: eu-central-1
role-to-assume: ${{ inputs.aws-oidc-role-arn }}
role-duration-seconds: 3600 # 1 hour should be more than enough to upload report
ALLURE_VERSION: 2.27.0
ALLURE_ZIP_SHA256: b071858fb2fa542c65d8f152c5c40d26267b2dfb74df1f1608a589ecca38e777
# Potentially we could have several running build for the same key (for example, for the main branch), so we use improvised lock for this
- name: Acquire lock
@@ -195,7 +183,7 @@ runs:
uses: actions/cache@v4
with:
path: ~/.cache/pypoetry/virtualenvs
key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-bookworm-${{ hashFiles('poetry.lock') }}
key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-${{ hashFiles('poetry.lock') }}
- name: Store Allure test stat in the DB (new)
if: ${{ !cancelled() && inputs.store-test-results-into-db == 'true' }}
@@ -233,8 +221,6 @@ runs:
REPORT_URL: ${{ steps.generate-report.outputs.report-url }}
COMMIT_SHA: ${{ github.event.pull_request.head.sha || github.sha }}
with:
# Retry script for 5XX server errors: https://github.com/actions/github-script#retries
retries: 5
script: |
const { REPORT_URL, COMMIT_SHA } = process.env

View File

@@ -8,9 +8,6 @@ inputs:
unique-key:
description: 'string to distinguish different results in the same run'
required: true
aws-oidc-role-arn:
description: 'OIDC role arn to interract with S3'
required: true
runs:
using: "composite"
@@ -18,14 +15,11 @@ runs:
steps:
- name: Set variables
shell: bash -euxo pipefail {0}
env:
PR_NUMBER: ${{ github.event.pull_request.number }}
REPORT_DIR: ${{ inputs.report-dir }}
run: |
if [ -n "${PR_NUMBER}" ]; then
PR_NUMBER=$(jq --raw-output .pull_request.number "$GITHUB_EVENT_PATH" || true)
if [ "${PR_NUMBER}" != "null" ]; then
BRANCH_OR_PR=pr-${PR_NUMBER}
elif [ "${GITHUB_REF_NAME}" = "main" ] || [ "${GITHUB_REF_NAME}" = "release" ] || \
[ "${GITHUB_REF_NAME}" = "release-proxy" ] || [ "${GITHUB_REF_NAME}" = "release-compute" ]; then
elif [ "${GITHUB_REF_NAME}" = "main" ] || [ "${GITHUB_REF_NAME}" = "release" ] || [ "${GITHUB_REF_NAME}" = "release-proxy" ]; then
# Shortcut for special branches
BRANCH_OR_PR=${GITHUB_REF_NAME}
else
@@ -34,13 +28,8 @@ runs:
echo "BRANCH_OR_PR=${BRANCH_OR_PR}" >> $GITHUB_ENV
echo "REPORT_DIR=${REPORT_DIR}" >> $GITHUB_ENV
- uses: aws-actions/configure-aws-credentials@v4
if: ${{ !cancelled() }}
with:
aws-region: eu-central-1
role-to-assume: ${{ inputs.aws-oidc-role-arn }}
role-duration-seconds: 3600 # 1 hour should be more than enough to upload report
env:
REPORT_DIR: ${{ inputs.report-dir }}
- name: Upload test results
shell: bash -euxo pipefail {0}

View File

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

View File

@@ -84,13 +84,7 @@ runs:
--header "Authorization: Bearer ${API_KEY}"
)
role_name=$(echo "$roles" | jq --raw-output '
(.roles | map(select(.protected == false))) as $roles |
if any($roles[]; .name == "neondb_owner")
then "neondb_owner"
else $roles[0].name
end
')
role_name=$(echo $roles | jq --raw-output '.roles[] | select(.protected == false) | .name')
echo "role_name=${role_name}" >> $GITHUB_OUTPUT
env:
API_HOST: ${{ inputs.api_host }}
@@ -113,13 +107,13 @@ runs:
)
if [ -z "${reset_password}" ]; then
sleep $i
sleep 1
continue
fi
password=$(echo $reset_password | jq --raw-output '.role.password')
if [ "${password}" == "null" ]; then
sleep $i # increasing backoff
sleep 1
continue
fi

View File

@@ -17,38 +17,6 @@ inputs:
compute_units:
description: '[Min, Max] compute units'
default: '[1, 1]'
# settings below only needed if you want the project to be sharded from the beginning
shard_split_project:
description: 'by default new projects are not shard-split initiailly, but only when shard-split threshold is reached, specify true to explicitly shard-split initially'
required: false
default: 'false'
disable_sharding:
description: 'by default new projects use storage controller default policy to shard-split when shard-split threshold is reached, specify true to explicitly disable sharding'
required: false
default: 'false'
admin_api_key:
description: 'Admin API Key needed for shard-splitting. Must be specified if shard_split_project is true'
required: false
shard_count:
description: 'Number of shards to split the project into, only applies if shard_split_project is true'
required: false
default: '8'
stripe_size:
description: 'Stripe size, optional, in 8kiB pages. e.g. set 2048 for 16MB stripes. Default is 128 MiB, only applies if shard_split_project is true'
required: false
default: '32768'
psql_path:
description: 'Path to psql binary - it is caller responsibility to provision the psql binary'
required: false
default: '/tmp/neon/pg_install/v16/bin/psql'
libpq_lib_path:
description: 'Path to directory containing libpq library - it is caller responsibility to provision the libpq library'
required: false
default: '/tmp/neon/pg_install/v16/lib'
project_settings:
description: 'A JSON object with project settings'
required: false
default: '{}'
outputs:
dsn:
@@ -66,9 +34,9 @@ runs:
# A shell without `set -x` to not to expose password/dsn in logs
shell: bash -euo pipefail {0}
run: |
res=$(curl \
project=$(curl \
"https://${API_HOST}/api/v2/projects" \
-w "%{http_code}" \
--fail \
--header "Accept: application/json" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${API_KEY}" \
@@ -80,18 +48,9 @@ runs:
\"provisioner\": \"k8s-neonvm\",
\"autoscaling_limit_min_cu\": ${MIN_CU},
\"autoscaling_limit_max_cu\": ${MAX_CU},
\"settings\": ${PROJECT_SETTINGS}
\"settings\": { }
}
}")
code=${res: -3}
if [[ ${code} -ge 400 ]]; then
echo Request failed with error code ${code}
echo ${res::-3}
exit 1
else
project=${res::-3}
fi
# Mask password
echo "::add-mask::$(echo $project | jq --raw-output '.roles[] | select(.name != "web_access") | .password')"
@@ -104,39 +63,6 @@ runs:
echo "project_id=${project_id}" >> $GITHUB_OUTPUT
echo "Project ${project_id} has been created"
if [ "${SHARD_SPLIT_PROJECT}" = "true" ]; then
# determine tenant ID
TENANT_ID=`${PSQL} ${dsn} -t -A -c "SHOW neon.tenant_id"`
echo "Splitting project ${project_id} with tenant_id ${TENANT_ID} into $((SHARD_COUNT)) shards with stripe size $((STRIPE_SIZE))"
echo "Sending PUT request to https://${API_HOST}/regions/${REGION_ID}/api/v1/admin/storage/proxy/control/v1/tenant/${TENANT_ID}/shard_split"
echo "with body {\"new_shard_count\": $((SHARD_COUNT)), \"new_stripe_size\": $((STRIPE_SIZE))}"
# we need an ADMIN API KEY to invoke storage controller API for shard splitting (bash -u above checks that the variable is set)
curl -X PUT \
"https://${API_HOST}/regions/${REGION_ID}/api/v1/admin/storage/proxy/control/v1/tenant/${TENANT_ID}/shard_split" \
-H "Accept: application/json" -H "Content-Type: application/json" -H "Authorization: Bearer ${ADMIN_API_KEY}" \
-d "{\"new_shard_count\": $SHARD_COUNT, \"new_stripe_size\": $STRIPE_SIZE}"
fi
if [ "${DISABLE_SHARDING}" = "true" ]; then
# determine tenant ID
TENANT_ID=`${PSQL} ${dsn} -t -A -c "SHOW neon.tenant_id"`
echo "Explicitly disabling shard-splitting for project ${project_id} with tenant_id ${TENANT_ID}"
echo "Sending PUT request to https://${API_HOST}/regions/${REGION_ID}/api/v1/admin/storage/proxy/control/v1/tenant/${TENANT_ID}/policy"
echo "with body {\"scheduling\": \"Essential\"}"
# we need an ADMIN API KEY to invoke storage controller API for shard splitting (bash -u above checks that the variable is set)
curl -X PUT \
"https://${API_HOST}/regions/${REGION_ID}/api/v1/admin/storage/proxy/control/v1/tenant/${TENANT_ID}/policy" \
-H "Accept: application/json" -H "Content-Type: application/json" -H "Authorization: Bearer ${ADMIN_API_KEY}" \
-d "{\"scheduling\": \"Essential\"}"
fi
env:
API_HOST: ${{ inputs.api_host }}
API_KEY: ${{ inputs.api_key }}
@@ -144,11 +70,3 @@ runs:
POSTGRES_VERSION: ${{ inputs.postgres_version }}
MIN_CU: ${{ fromJSON(inputs.compute_units)[0] }}
MAX_CU: ${{ fromJSON(inputs.compute_units)[1] }}
SHARD_SPLIT_PROJECT: ${{ inputs.shard_split_project }}
DISABLE_SHARDING: ${{ inputs.disable_sharding }}
ADMIN_API_KEY: ${{ inputs.admin_api_key }}
SHARD_COUNT: ${{ inputs.shard_count }}
STRIPE_SIZE: ${{ inputs.stripe_size }}
PSQL: ${{ inputs.psql_path }}
LD_LIBRARY_PATH: ${{ inputs.libpq_lib_path }}
PROJECT_SETTINGS: ${{ inputs.project_settings }}

View File

@@ -1,28 +0,0 @@
name: 'Prepare current job for subzero'
description: >
Set git token to access `neondatabase/subzero` from cargo build,
and set `CARGO_NET_GIT_FETCH_WITH_CLI=true` env variable to use git CLI
inputs:
token:
description: 'GitHub token with access to neondatabase/subzero'
required: true
runs:
using: "composite"
steps:
- name: Set git token for neondatabase/subzero
uses: pyTooling/Actions/with-post-step@2307b526df64d55e95884e072e49aac2a00a9afa # v5.1.0
env:
SUBZERO_ACCESS_TOKEN: ${{ inputs.token }}
with:
main: |
git config --global url."https://x-access-token:${SUBZERO_ACCESS_TOKEN}@github.com/neondatabase/subzero".insteadOf "https://github.com/neondatabase/subzero"
cargo add -p proxy subzero-core --git https://github.com/neondatabase/subzero --rev 396264617e78e8be428682f87469bb25429af88a
post: |
git config --global --unset url."https://x-access-token:${SUBZERO_ACCESS_TOKEN}@github.com/neondatabase/subzero".insteadOf "https://github.com/neondatabase/subzero"
- name: Set `CARGO_NET_GIT_FETCH_WITH_CLI=true` env variable
shell: bash -euxo pipefail {0}
run: echo "CARGO_NET_GIT_FETCH_WITH_CLI=true" >> ${GITHUB_ENV}

View File

@@ -36,26 +36,18 @@ inputs:
description: 'Region name for real s3 tests'
required: false
default: ''
rerun_failed:
description: 'Whether to rerun failed tests'
rerun_flaky:
description: 'Whether to rerun flaky tests'
required: false
default: 'false'
pg_version:
description: 'Postgres version to use for tests'
required: false
default: 'v16'
sanitizers:
description: 'enabled or disabled'
required: false
default: 'disabled'
type: string
benchmark_durations:
description: 'benchmark durations JSON'
required: false
default: '{}'
aws-oidc-role-arn:
description: 'OIDC role arn to interract with S3'
required: true
runs:
using: "composite"
@@ -64,9 +56,8 @@ runs:
if: inputs.build_type != 'remote'
uses: ./.github/actions/download
with:
name: neon-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build_type }}${{ inputs.sanitizers == 'enabled' && '-sanitized' || '' }}-artifact
name: neon-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build_type }}-artifact
path: /tmp/neon
aws-oidc-role-arn: ${{ inputs.aws-oidc-role-arn }}
- name: Download Neon binaries for the previous release
if: inputs.build_type != 'remote'
@@ -75,7 +66,6 @@ runs:
name: neon-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build_type }}-artifact
path: /tmp/neon-previous
prefix: latest
aws-oidc-role-arn: ${{ inputs.aws-oidc-role-arn }}
- name: Download compatibility snapshot
if: inputs.build_type != 'remote'
@@ -87,7 +77,6 @@ runs:
# The lack of compatibility snapshot (for example, for the new Postgres version)
# shouldn't fail the whole job. Only relevant test should fail.
skip-if-does-not-exist: true
aws-oidc-role-arn: ${{ inputs.aws-oidc-role-arn }}
- name: Checkout
if: inputs.needs_postgres_source == 'true'
@@ -99,7 +88,7 @@ runs:
uses: actions/cache@v4
with:
path: ~/.cache/pypoetry/virtualenvs
key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-bookworm-${{ hashFiles('poetry.lock') }}
key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-${{ hashFiles('poetry.lock') }}
- name: Install Python deps
shell: bash -euxo pipefail {0}
@@ -113,9 +102,10 @@ runs:
TEST_OUTPUT: /tmp/test_output
BUILD_TYPE: ${{ inputs.build_type }}
COMPATIBILITY_SNAPSHOT_DIR: /tmp/compatibility_snapshot_pg${{ inputs.pg_version }}
RERUN_FAILED: ${{ inputs.rerun_failed }}
ALLOW_BACKWARD_COMPATIBILITY_BREAKAGE: contains(github.event.pull_request.labels.*.name, 'backward compatibility breakage')
ALLOW_FORWARD_COMPATIBILITY_BREAKAGE: contains(github.event.pull_request.labels.*.name, 'forward compatibility breakage')
RERUN_FLAKY: ${{ inputs.rerun_flaky }}
PG_VERSION: ${{ inputs.pg_version }}
SANITIZERS: ${{ inputs.sanitizers }}
shell: bash -euxo pipefail {0}
run: |
# PLATFORM will be embedded in the perf test report
@@ -125,15 +115,12 @@ runs:
export DEFAULT_PG_VERSION=${PG_VERSION#v}
export LD_LIBRARY_PATH=${POSTGRES_DISTRIB_DIR}/v${DEFAULT_PG_VERSION}/lib
export BENCHMARK_CONNSTR=${BENCHMARK_CONNSTR:-}
export ASAN_OPTIONS=detect_leaks=0:detect_stack_use_after_return=0:abort_on_error=1:strict_string_checks=1:check_initialization_order=1:strict_init_order=1
export UBSAN_OPTIONS=abort_on_error=1:print_stacktrace=1
if [ "${BUILD_TYPE}" = "remote" ]; then
export REMOTE_ENV=1
fi
PERF_REPORT_DIR="$(realpath test_runner/perf-report-local)"
echo "PERF_REPORT_DIR=${PERF_REPORT_DIR}" >> ${GITHUB_ENV}
rm -rf $PERF_REPORT_DIR
TEST_SELECTION="test_runner/${{ inputs.test_selection }}"
@@ -163,8 +150,15 @@ runs:
EXTRA_PARAMS="--out-dir $PERF_REPORT_DIR $EXTRA_PARAMS"
fi
if [ "${RERUN_FAILED}" == "true" ]; then
EXTRA_PARAMS="--reruns 2 $EXTRA_PARAMS"
if [ "${RERUN_FLAKY}" == "true" ]; then
mkdir -p $TEST_OUTPUT
poetry run ./scripts/flaky_tests.py "${TEST_RESULT_CONNSTR}" \
--days 7 \
--output "$TEST_OUTPUT/flaky.json" \
--pg-version "${DEFAULT_PG_VERSION}" \
--build-type "${BUILD_TYPE}"
EXTRA_PARAMS="--flaky-tests-json $TEST_OUTPUT/flaky.json $EXTRA_PARAMS"
fi
# We use pytest-split plugin to run benchmarks in parallel on different CI runners
@@ -176,13 +170,7 @@ runs:
fi
if [[ $BUILD_TYPE == "debug" && $RUNNER_ARCH == 'X64' ]]; then
# We don't use code coverage for regression tests (the step is disabled),
# so there's no need to collect it.
# Ref https://github.com/neondatabase/neon/issues/4540
# cov_prefix=(scripts/coverage "--profraw-prefix=$GITHUB_JOB" --dir=/tmp/coverage run)
cov_prefix=()
# Explicitly set LLVM_PROFILE_FILE to /dev/null to avoid writing *.profraw files
export LLVM_PROFILE_FILE=/dev/null
cov_prefix=(scripts/coverage "--profraw-prefix=$GITHUB_JOB" --dir=/tmp/coverage run)
else
cov_prefix=()
fi
@@ -216,12 +204,11 @@ runs:
--verbose \
-rA $TEST_SELECTION $EXTRA_PARAMS
- name: Upload performance report
if: ${{ !cancelled() && inputs.save_perf_report == 'true' }}
shell: bash -euxo pipefail {0}
run: |
export REPORT_FROM="${PERF_REPORT_DIR}"
scripts/generate_and_push_perf_report.sh
if [[ "${{ inputs.save_perf_report }}" == "true" ]]; then
export REPORT_FROM="$PERF_REPORT_DIR"
export REPORT_TO="$PLATFORM"
scripts/generate_and_push_perf_report.sh
fi
- name: Upload compatibility snapshot
# Note, that we use `github.base_ref` which is a target branch for a PR
@@ -231,22 +218,10 @@ runs:
name: compatibility-snapshot-${{ runner.arch }}-${{ inputs.build_type }}-pg${{ inputs.pg_version }}
# Directory is created by test_compatibility.py::test_create_snapshot, keep the path in sync with the test
path: /tmp/test_output/compatibility_snapshot_pg${{ inputs.pg_version }}/
# The lack of compatibility snapshot shouldn't fail the job
# (for example if we didn't run the test for non build-and-test workflow)
skip-if-does-not-exist: true
aws-oidc-role-arn: ${{ inputs.aws-oidc-role-arn }}
- uses: aws-actions/configure-aws-credentials@v4
if: ${{ !cancelled() }}
with:
aws-region: eu-central-1
role-to-assume: ${{ inputs.aws-oidc-role-arn }}
role-duration-seconds: 3600 # 1 hour should be more than enough to upload report
- name: Upload test results
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-store
with:
report-dir: /tmp/test_output/allure/results
unique-key: ${{ inputs.build_type }}-${{ inputs.pg_version }}-${{ runner.arch }}
aws-oidc-role-arn: ${{ inputs.aws-oidc-role-arn }}
unique-key: ${{ inputs.build_type }}-${{ inputs.pg_version }}

View File

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

View File

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

View File

@@ -7,28 +7,18 @@ inputs:
path:
description: "A directory or file to upload"
required: true
skip-if-does-not-exist:
description: "Allow to skip if path doesn't exist, fail otherwise"
default: false
required: false
prefix:
description: "S3 prefix. Default is '${GITHUB_SHA}/${GITHUB_RUN_ID}/${GITHUB_RUN_ATTEMPT}'"
required: false
aws-oidc-role-arn:
description: "the OIDC role arn for aws auth"
required: false
default: ""
runs:
using: "composite"
steps:
- name: Prepare artifact
id: prepare-artifact
shell: bash -euxo pipefail {0}
env:
SOURCE: ${{ inputs.path }}
ARCHIVE: /tmp/uploads/${{ inputs.name }}.tar.zst
SKIP_IF_DOES_NOT_EXIST: ${{ inputs.skip-if-does-not-exist }}
run: |
mkdir -p $(dirname $ARCHIVE)
@@ -43,29 +33,14 @@ runs:
elif [ -f ${SOURCE} ]; then
time tar -cf ${ARCHIVE} --zstd ${SOURCE}
elif ! ls ${SOURCE} > /dev/null 2>&1; then
if [ "${SKIP_IF_DOES_NOT_EXIST}" = "true" ]; then
echo 'SKIPPED=true' >> $GITHUB_OUTPUT
exit 0
else
echo >&2 "${SOURCE} does not exist"
exit 2
fi
echo >&2 "${SOURCE} does not exist"
exit 2
else
echo >&2 "${SOURCE} is neither a directory nor a file, do not know how to handle it"
exit 3
fi
echo 'SKIPPED=false' >> $GITHUB_OUTPUT
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: eu-central-1
role-to-assume: ${{ inputs.aws-oidc-role-arn }}
role-duration-seconds: 3600
- name: Upload artifact
if: ${{ steps.prepare-artifact.outputs.SKIPPED == 'false' }}
shell: bash -euxo pipefail {0}
env:
SOURCE: ${{ inputs.path }}

View File

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

View File

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

View File

@@ -1,69 +0,0 @@
import itertools
import json
import os
import sys
source_tag = os.getenv("SOURCE_TAG")
target_tag = os.getenv("TARGET_TAG")
branch = os.getenv("BRANCH")
dev_acr = os.getenv("DEV_ACR")
prod_acr = os.getenv("PROD_ACR")
dev_aws = os.getenv("DEV_AWS")
prod_aws = os.getenv("PROD_AWS")
aws_region = os.getenv("AWS_REGION")
components = {
"neon": ["neon"],
"compute": [
"compute-node-v14",
"compute-node-v15",
"compute-node-v16",
"compute-node-v17",
"vm-compute-node-v14",
"vm-compute-node-v15",
"vm-compute-node-v16",
"vm-compute-node-v17",
],
}
registries = {
"dev": [
"docker.io/neondatabase",
"ghcr.io/neondatabase",
f"{dev_aws}.dkr.ecr.{aws_region}.amazonaws.com",
f"{dev_acr}.azurecr.io/neondatabase",
],
"prod": [
f"{prod_aws}.dkr.ecr.{aws_region}.amazonaws.com",
f"{prod_acr}.azurecr.io/neondatabase",
],
}
release_branches = ["release", "release-proxy", "release-compute"]
outputs: dict[str, dict[str, list[str]]] = {}
target_tags = (
[target_tag, "latest"]
if branch == "main"
else [target_tag, "released"]
if branch in release_branches
else [target_tag]
)
target_stages = ["dev", "prod"] if branch in release_branches else ["dev"]
for component_name, component_images in components.items():
for stage in target_stages:
outputs[f"{component_name}-{stage}"] = {
f"ghcr.io/neondatabase/{component_image}:{source_tag}": [
f"{registry}/{component_image}:{tag}"
for registry, tag in itertools.product(registries[stage], target_tags)
if not (registry == "ghcr.io/neondatabase" and tag == source_tag)
]
for component_image in component_images
}
with open(os.getenv("GITHUB_OUTPUT", "/dev/null"), "a") as f:
for key, value in outputs.items():
f.write(f"{key}={json.dumps(value)}\n")
print(f"Image map for {key}:\n{json.dumps(value, indent=2)}\n\n", file=sys.stderr)

View File

@@ -1,110 +0,0 @@
#!/usr/bin/env bash
set -euo pipefail
DOCS_URL="https://docs.neon.build/overview/repositories/neon.html"
message() {
if [[ -n "${GITHUB_PR_NUMBER:-}" ]]; then
gh pr comment --repo "${GITHUB_REPOSITORY}" "${GITHUB_PR_NUMBER}" --edit-last --body "$1" \
|| gh pr comment --repo "${GITHUB_REPOSITORY}" "${GITHUB_PR_NUMBER}" --body "$1"
fi
echo "$1"
}
report_error() {
message "$1
For more details, see the documentation: ${DOCS_URL}"
exit 1
}
case "$RELEASE_BRANCH" in
"release") COMPONENT="Storage" ;;
"release-proxy") COMPONENT="Proxy" ;;
"release-compute") COMPONENT="Compute" ;;
*)
report_error "Unknown release branch: ${RELEASE_BRANCH}"
;;
esac
# Identify main and release branches
MAIN_BRANCH="origin/main"
REMOTE_RELEASE_BRANCH="origin/${RELEASE_BRANCH}"
# Find merge base
MERGE_BASE=$(git merge-base "${MAIN_BRANCH}" "${REMOTE_RELEASE_BRANCH}")
echo "Merge base of ${MAIN_BRANCH} and ${RELEASE_BRANCH}: ${MERGE_BASE}"
# Get the HEAD commit (last commit in PR, expected to be the merge commit)
LAST_COMMIT=$(git rev-parse HEAD)
MERGE_COMMIT_MESSAGE=$(git log -1 --format=%s "${LAST_COMMIT}")
EXPECTED_MESSAGE_REGEX="^$COMPONENT release [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2} UTC$"
if ! [[ "${MERGE_COMMIT_MESSAGE}" =~ ${EXPECTED_MESSAGE_REGEX} ]]; then
report_error "Merge commit message does not match expected pattern: '<component> release YYYY-MM-DD'
Expected component: ${COMPONENT}
Found: '${MERGE_COMMIT_MESSAGE}'"
fi
echo "✅ Merge commit message is correctly formatted: '${MERGE_COMMIT_MESSAGE}'"
LAST_COMMIT_PARENTS=$(git cat-file -p "${LAST_COMMIT}" | jq -sR '[capture("parent (?<parent>[0-9a-f]{40})"; "g") | .parent]')
if [[ "$(echo "${LAST_COMMIT_PARENTS}" | jq 'length')" -ne 2 ]]; then
report_error "Last commit must be a merge commit with exactly two parents"
fi
EXPECTED_RELEASE_HEAD=$(git rev-parse "${REMOTE_RELEASE_BRANCH}")
if echo "${LAST_COMMIT_PARENTS}" | jq -e --arg rel "${EXPECTED_RELEASE_HEAD}" 'index($rel) != null' > /dev/null; then
LINEAR_HEAD=$(echo "${LAST_COMMIT_PARENTS}" | jq -r '[.[] | select(. != $rel)][0]' --arg rel "${EXPECTED_RELEASE_HEAD}")
else
report_error "Last commit must merge the release branch (${RELEASE_BRANCH})"
fi
echo "✅ Last commit correctly merges the previous commit and the release branch"
echo "Top commit of linear history: ${LINEAR_HEAD}"
MERGE_COMMIT_TREE=$(git rev-parse "${LAST_COMMIT}^{tree}")
LINEAR_HEAD_TREE=$(git rev-parse "${LINEAR_HEAD}^{tree}")
if [[ "${MERGE_COMMIT_TREE}" != "${LINEAR_HEAD_TREE}" ]]; then
report_error "Tree of merge commit (${MERGE_COMMIT_TREE}) does not match tree of linear history head (${LINEAR_HEAD_TREE})
This indicates that the merge of ${RELEASE_BRANCH} into this branch was not performed using the merge strategy 'ours'"
fi
echo "✅ Merge commit tree matches the linear history head"
EXPECTED_PREVIOUS_COMMIT="${LINEAR_HEAD}"
# Now traverse down the history, ensuring each commit has exactly one parent
CURRENT_COMMIT="${EXPECTED_PREVIOUS_COMMIT}"
while [[ "${CURRENT_COMMIT}" != "${MERGE_BASE}" && "${CURRENT_COMMIT}" != "${EXPECTED_RELEASE_HEAD}" ]]; do
CURRENT_COMMIT_PARENTS=$(git cat-file -p "${CURRENT_COMMIT}" | jq -sR '[capture("parent (?<parent>[0-9a-f]{40})"; "g") | .parent]')
if [[ "$(echo "${CURRENT_COMMIT_PARENTS}" | jq 'length')" -ne 1 ]]; then
report_error "Commit ${CURRENT_COMMIT} must have exactly one parent"
fi
NEXT_COMMIT=$(echo "${CURRENT_COMMIT_PARENTS}" | jq -r '.[0]')
if [[ "${NEXT_COMMIT}" == "${MERGE_BASE}" ]]; then
echo "✅ Reached merge base (${MERGE_BASE})"
PR_BASE="${MERGE_BASE}"
elif [[ "${NEXT_COMMIT}" == "${EXPECTED_RELEASE_HEAD}" ]]; then
echo "✅ Reached release branch (${EXPECTED_RELEASE_HEAD})"
PR_BASE="${EXPECTED_RELEASE_HEAD}"
elif [[ -z "${NEXT_COMMIT}" ]]; then
report_error "Unexpected end of commit history before reaching merge base"
fi
# Move to the next commit in the chain
CURRENT_COMMIT="${NEXT_COMMIT}"
done
echo "✅ All commits are properly ordered and linear"
echo "✅ Release PR structure is valid"
echo
message "Commits that are part of this release:
$(git log --oneline "${PR_BASE}..${LINEAR_HEAD}")"

View File

@@ -1,31 +0,0 @@
# Expects response from https://docs.github.com/en/rest/releases/releases?apiVersion=2022-11-28#list-releases as input,
# with tag names `release` for storage, `release-compute` for compute and `release-proxy` for proxy releases.
# Extract only the `tag_name` field from each release object
[ .[].tag_name ]
# Transform each tag name into a structured object using regex capture
| reduce map(
capture("^(?<full>release(-(?<component>proxy|compute))?-(?<version>\\d+))$")
| {
component: (.component // "storage"), # Default to "storage" if no component is specified
version: (.version | tonumber), # Convert the version number to an integer
full: .full # Store the full tag name for final output
}
)[] as $entry # Loop over the transformed list
# Accumulate the latest (highest-numbered) version for each component
({};
.[$entry.component] |= (if . == null or $entry.version > .version then $entry else . end))
# Ensure that each component exists, or fail
| (["storage", "compute", "proxy"] - (keys)) as $missing
| if ($missing | length) > 0 then
"Error: Found no release for \($missing | join(", "))!\n" | halt_error(1)
else . end
# Convert the resulting object into an array of formatted strings
| to_entries
| map("\(.key)=\(.value.full)")
# Output each string separately
| .[]

View File

@@ -1,45 +0,0 @@
import json
import os
import subprocess
RED = "\033[91m"
RESET = "\033[0m"
image_map = os.getenv("IMAGE_MAP")
if not image_map:
raise ValueError("IMAGE_MAP environment variable is not set")
try:
parsed_image_map: dict[str, list[str]] = json.loads(image_map)
except json.JSONDecodeError as e:
raise ValueError("Failed to parse IMAGE_MAP as JSON") from e
failures = []
pending = [(source, target) for source, targets in parsed_image_map.items() for target in targets]
while len(pending) > 0:
if len(failures) > 10:
print("Error: more than 10 failures!")
for failure in failures:
print(f'"{failure[0]}" failed with the following output:')
print(failure[1])
raise RuntimeError("Retry limit reached.")
source, target = pending.pop(0)
cmd = ["docker", "buildx", "imagetools", "create", "-t", target, source]
print(f"Running: {' '.join(cmd)}")
result = subprocess.run(cmd, text=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
if result.returncode != 0:
failures.append((" ".join(cmd), result.stdout, target))
pending.append((source, target))
print(
f"{RED}[RETRY]{RESET} Push failed for {target}. Retrying... (failure count: {len(failures)})"
)
print(result.stdout)
if len(failures) > 0 and (github_output := os.getenv("GITHUB_OUTPUT")):
failed_targets = [target for _, _, target in failures]
with open(github_output, "a") as f:
f.write(f"push_failures={json.dumps(failed_targets)}\n")

View File

@@ -3,26 +3,19 @@ name: Prepare benchmarking databases by restoring dumps
on:
workflow_call:
# no inputs needed
defaults:
run:
shell: bash -euxo pipefail {0}
permissions:
contents: read
jobs:
setup-databases:
permissions:
contents: write
statuses: write
id-token: write # aws-actions/configure-aws-credentials
strategy:
fail-fast: false
matrix:
platform: [ aws-rds-postgres, aws-aurora-serverless-v2-postgres, neon, neon_pg17 ]
platform: [ aws-rds-postgres, aws-aurora-serverless-v2-postgres, neon ]
database: [ clickbench, tpch, userexample ]
env:
LD_LIBRARY_PATH: /tmp/neon/pg_install/v16/lib
PLATFORM: ${{ matrix.platform }}
@@ -30,33 +23,22 @@ jobs:
runs-on: [ self-hosted, us-east-2, x64 ]
container:
image: ghcr.io/neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
image: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/build-tools:pinned
options: --init
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Set up Connection String
id: set-up-prep-connstr
run: |
case "${PLATFORM}" in
neon)
CONNSTR=${{ secrets.BENCHMARK_CAPTEST_CONNSTR }}
;;
neon_pg17)
CONNSTR=${{ secrets.BENCHMARK_CAPTEST_CONNSTR_PG17 }}
CONNSTR=${{ secrets.BENCHMARK_CAPTEST_CONNSTR }}
;;
aws-rds-postgres)
CONNSTR=${{ secrets.BENCHMARK_RDS_POSTGRES_CONNSTR }}
CONNSTR=${{ secrets.BENCHMARK_RDS_POSTGRES_CONNSTR }}
;;
aws-aurora-serverless-v2-postgres)
CONNSTR=${{ secrets.BENCHMARK_RDS_AURORA_CONNSTR }}
CONNSTR=${{ secrets.BENCHMARK_RDS_AURORA_CONNSTR }}
;;
*)
echo >&2 "Unknown PLATFORM=${PLATFORM}"
@@ -64,16 +46,9 @@ jobs:
;;
esac
echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 18000 # 5 hours
- uses: actions/checkout@v4
- name: Download Neon artifact
uses: ./.github/actions/download
@@ -81,25 +56,24 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
# we create a table that has one row for each database that we want to restore with the status whether the restore is done
# we create a table that has one row for each database that we want to restore with the status whether the restore is done
- name: Create benchmark_restore_status table if it does not exist
env:
BENCHMARK_CONNSTR: ${{ steps.set-up-prep-connstr.outputs.connstr }}
DATABASE_NAME: ${{ matrix.database }}
# to avoid a race condition of multiple jobs trying to create the table at the same time,
# to avoid a race condition of multiple jobs trying to create the table at the same time,
# we use an advisory lock
run: |
${PG_BINARIES}/psql "${{ env.BENCHMARK_CONNSTR }}" -c "
SELECT pg_advisory_lock(4711);
SELECT pg_advisory_lock(4711);
CREATE TABLE IF NOT EXISTS benchmark_restore_status (
databasename text primary key,
restore_done boolean
);
SELECT pg_advisory_unlock(4711);
"
- name: Check if restore is already done
id: check-restore-done
env:
@@ -133,7 +107,7 @@ jobs:
DATABASE_NAME: ${{ matrix.database }}
run: |
mkdir -p /tmp/dumps
aws s3 cp s3://neon-github-dev/performance/pgdumps/$DATABASE_NAME/$DATABASE_NAME.pg_dump /tmp/dumps/
aws s3 cp s3://neon-github-dev/performance/pgdumps/$DATABASE_NAME/$DATABASE_NAME.pg_dump /tmp/dumps/
- name: Replace database name in connection string
if: steps.check-restore-done.outputs.skip != 'true'
@@ -152,17 +126,17 @@ jobs:
else
new_connstr="${base_connstr}/${DATABASE_NAME}"
fi
echo "database_connstr=${new_connstr}" >> $GITHUB_OUTPUT
echo "database_connstr=${new_connstr}" >> $GITHUB_OUTPUT
- name: Restore dump
if: steps.check-restore-done.outputs.skip != 'true'
env:
DATABASE_NAME: ${{ matrix.database }}
DATABASE_CONNSTR: ${{ steps.replace-dbname.outputs.database_connstr }}
# the following works only with larger computes:
# the following works only with larger computes:
# PGOPTIONS: "-c maintenance_work_mem=8388608 -c max_parallel_maintenance_workers=7"
# we add the || true because:
# the dumps were created with Neon and contain neon extensions that are not
# the dumps were created with Neon and contain neon extensions that are not
# available in RDS, so we will always report an error, but we can ignore it
run: |
${PG_BINARIES}/pg_restore --clean --if-exists --no-owner --jobs=4 \

View File

@@ -19,30 +19,10 @@ on:
description: 'debug or release'
required: true
type: string
test-cfg:
description: 'a json object of postgres versions and lfc states to run regression tests on'
pg-versions:
description: 'a json array of postgres versions to run regression tests on'
required: true
type: string
sanitizers:
description: 'enabled or disabled'
required: false
default: 'disabled'
type: string
test-selection:
description: 'specification of selected test(s) to run'
required: false
default: ''
type: string
test-run-count:
description: 'number of runs to perform for selected tests'
required: false
default: 1
type: number
rerun-failed:
description: 'rerun failed tests to ignore flaky tests'
required: false
default: true
type: boolean
defaults:
run:
@@ -51,21 +31,17 @@ defaults:
env:
RUST_BACKTRACE: 1
COPT: '-Werror'
permissions:
contents: read
AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
jobs:
build-neon:
runs-on: ${{ fromJSON(format('["self-hosted", "{0}"]', inputs.arch == 'arm64' && 'large-arm64' || 'large')) }}
permissions:
id-token: write # aws-actions/configure-aws-credentials
contents: read
runs-on: ${{ fromJson(format('["self-hosted", "{0}"]', inputs.arch == 'arm64' && 'large-arm64' || 'large')) }}
container:
image: ${{ inputs.build-tools-image }}
credentials:
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
# Raise locked memory limit for tokio-epoll-uring.
# On 5.10 LTS kernels < 5.10.162 (and generally mainline kernels < 5.12),
# io_uring will account the memory of the CQ and SQ as locked.
@@ -77,19 +53,24 @@ jobs:
BUILD_TAG: ${{ inputs.build-tag }}
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Fix git ownership
run: |
# Workaround for `fatal: detected dubious ownership in repository at ...`
#
# Use both ${{ github.workspace }} and ${GITHUB_WORKSPACE} because they're different on host and in containers
# Ref https://github.com/actions/checkout/issues/785
#
git config --global --add safe.directory ${{ github.workspace }}
git config --global --add safe.directory ${GITHUB_WORKSPACE}
for r in 14 15 16 17; do
git config --global --add safe.directory "${{ github.workspace }}/vendor/postgres-v$r"
git config --global --add safe.directory "${GITHUB_WORKSPACE}/vendor/postgres-v$r"
done
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- uses: actions/checkout@v4
with:
submodules: true
- uses: ./.github/actions/prepare-for-subzero
with:
token: ${{ secrets.CI_ACCESS_TOKEN }}
- name: Set pg 14 revision for caching
id: pg_v14_rev
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v14) >> $GITHUB_OUTPUT
@@ -108,114 +89,102 @@ jobs:
# Set some environment variables used by all the steps.
#
# CARGO_FLAGS is extra options to pass to all "cargo" subcommands.
# CARGO_FLAGS is extra options to pass to "cargo build", "cargo test" etc.
# It also includes --features, if any
#
# CARGO_PROFILE is passed to "cargo build", "cargo test" etc, but not to
# "cargo metadata", because it doesn't accept --release or --debug options.
# CARGO_FEATURES is passed to "cargo metadata". It is separate from CARGO_FLAGS,
# because "cargo metadata" doesn't accept --release or --debug options
#
# We run tests with addtional features, that are turned off by default (e.g. in release builds), see
# corresponding Cargo.toml files for their descriptions.
- name: Set env variables
env:
ARCH: ${{ inputs.arch }}
SANITIZERS: ${{ inputs.sanitizers }}
run: |
CARGO_FLAGS="--locked --features testing,rest_broker"
CARGO_FEATURES="--features testing"
if [[ $BUILD_TYPE == "debug" && $ARCH == 'x64' ]]; then
cov_prefix="scripts/coverage --profraw-prefix=$GITHUB_JOB --dir=/tmp/coverage run"
CARGO_PROFILE=""
CARGO_FLAGS="--locked"
elif [[ $BUILD_TYPE == "debug" ]]; then
cov_prefix=""
CARGO_PROFILE=""
CARGO_FLAGS="--locked"
elif [[ $BUILD_TYPE == "release" ]]; then
cov_prefix=""
CARGO_PROFILE="--release"
fi
if [[ $SANITIZERS == 'enabled' ]]; then
make_vars="WITH_SANITIZERS=yes"
else
make_vars=""
CARGO_FLAGS="--locked --release"
fi
{
echo "cov_prefix=${cov_prefix}"
echo "make_vars=${make_vars}"
echo "CARGO_FEATURES=${CARGO_FEATURES}"
echo "CARGO_FLAGS=${CARGO_FLAGS}"
echo "CARGO_PROFILE=${CARGO_PROFILE}"
echo "CARGO_HOME=${GITHUB_WORKSPACE}/.cargo"
} >> $GITHUB_ENV
- name: Cache postgres v14 build
id: cache_pg_14
uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1 # v1.8.0
uses: actions/cache@v4
with:
endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
use-fallback: false
path: pg_install/v14
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v14_rev.outputs.pg_rev }}-bookworm-${{ hashFiles('Makefile', 'build-tools/Dockerfile') }}
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v14_rev.outputs.pg_rev }}-${{ hashFiles('Makefile', 'Dockerfile.build-tools') }}
- name: Cache postgres v15 build
id: cache_pg_15
uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1 # v1.8.0
uses: actions/cache@v4
with:
endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
use-fallback: false
path: pg_install/v15
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v15_rev.outputs.pg_rev }}-bookworm-${{ hashFiles('Makefile', 'build-tools/Dockerfile') }}
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v15_rev.outputs.pg_rev }}-${{ hashFiles('Makefile', 'Dockerfile.build-tools') }}
- name: Cache postgres v16 build
id: cache_pg_16
uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1 # v1.8.0
uses: actions/cache@v4
with:
endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
use-fallback: false
path: pg_install/v16
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v16_rev.outputs.pg_rev }}-bookworm-${{ hashFiles('Makefile', 'build-tools/Dockerfile') }}
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v16_rev.outputs.pg_rev }}-${{ hashFiles('Makefile', 'Dockerfile.build-tools') }}
- name: Cache postgres v17 build
id: cache_pg_17
uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1 # v1.8.0
uses: actions/cache@v4
with:
endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
use-fallback: false
path: pg_install/v17
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v17_rev.outputs.pg_rev }}-bookworm-${{ hashFiles('Makefile', 'build-tools/Dockerfile') }}
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v17_rev.outputs.pg_rev }}-${{ hashFiles('Makefile', 'Dockerfile.build-tools') }}
- name: Build all
# Note: the Makefile picks up BUILD_TYPE and CARGO_PROFILE from the env variables
run: mold -run make ${make_vars} all -j$(nproc) CARGO_BUILD_FLAGS="$CARGO_FLAGS"
- name: Build postgres v14
if: steps.cache_pg_14.outputs.cache-hit != 'true'
run: mold -run make postgres-v14 -j$(nproc)
- name: Build postgres v15
if: steps.cache_pg_15.outputs.cache-hit != 'true'
run: mold -run make postgres-v15 -j$(nproc)
- name: Build postgres v16
if: steps.cache_pg_16.outputs.cache-hit != 'true'
run: mold -run make postgres-v16 -j$(nproc)
- name: Build postgres v17
if: steps.cache_pg_17.outputs.cache-hit != 'true'
run: mold -run make postgres-v17 -j$(nproc)
- name: Build neon extensions
run: mold -run make neon-pg-ext -j$(nproc)
- name: Build walproposer-lib
run: mold -run make ${make_vars} walproposer-lib -j$(nproc)
run: mold -run make walproposer-lib -j$(nproc)
- name: Build unit tests
if: inputs.sanitizers != 'enabled'
- name: Run cargo build
run: |
export ASAN_OPTIONS=detect_leaks=0
${cov_prefix} mold -run cargo build $CARGO_FLAGS $CARGO_PROFILE --tests
PQ_LIB_DIR=$(pwd)/pg_install/v16/lib
export PQ_LIB_DIR
${cov_prefix} mold -run cargo build $CARGO_FLAGS $CARGO_FEATURES --bins --tests
# Do install *before* running rust tests because they might recompile the
# binaries with different features/flags.
- name: Install rust binaries
env:
ARCH: ${{ inputs.arch }}
SANITIZERS: ${{ inputs.sanitizers }}
run: |
# Install target binaries
mkdir -p /tmp/neon/bin/
binaries=$(
${cov_prefix} cargo metadata $CARGO_FLAGS --format-version=1 --no-deps |
${cov_prefix} cargo metadata $CARGO_FEATURES --format-version=1 --no-deps |
jq -r '.packages[].targets[] | select(.kind | index("bin")) | .name'
)
for bin in $binaries; do
@@ -225,14 +194,14 @@ jobs:
done
# Install test executables and write list of all binaries (for code coverage)
if [[ $BUILD_TYPE == "debug" && $ARCH == 'x64' && $SANITIZERS != 'enabled' ]]; then
if [[ $BUILD_TYPE == "debug" && $ARCH == 'x64' ]]; then
# Keep bloated coverage data files away from the rest of the artifact
mkdir -p /tmp/coverage/
mkdir -p /tmp/neon/test_bin/
test_exe_paths=$(
${cov_prefix} cargo test $CARGO_FLAGS $CARGO_PROFILE --message-format=json --no-run |
${cov_prefix} cargo test $CARGO_FLAGS $CARGO_FEATURES --message-format=json --no-run |
jq -r '.executable | select(. != null)'
)
for bin in $test_exe_paths; do
@@ -250,41 +219,33 @@ jobs:
done
fi
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 18000 # 5 hours
- name: Run rust tests
if: ${{ inputs.sanitizers != 'enabled' }}
env:
NEXTEST_RETRIES: 3
run: |
PQ_LIB_DIR=$(pwd)/pg_install/v16/lib
export PQ_LIB_DIR
LD_LIBRARY_PATH=$(pwd)/pg_install/v17/lib
export LD_LIBRARY_PATH
#nextest does not yet support running doctests
${cov_prefix} cargo test --doc $CARGO_FLAGS $CARGO_PROFILE
${cov_prefix} cargo test --doc $CARGO_FLAGS $CARGO_FEATURES
# run all non-pageserver tests
${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_PROFILE -E '!package(pageserver)'
${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_FEATURES -E '!package(pageserver)'
# run pageserver tests
# (When developing new pageserver features gated by config fields, we commonly make the rust
# unit tests sensitive to an environment variable NEON_PAGESERVER_UNIT_TEST_FEATURENAME.
# Then run the nextest invocation below for all relevant combinations. Singling out the
# pageserver tests from non-pageserver tests cuts down the time it takes for this CI step.)
NEON_PAGESERVER_UNIT_TEST_VIRTUAL_FILE_IOENGINE=tokio-epoll-uring \
${cov_prefix} \
cargo nextest run $CARGO_FLAGS $CARGO_PROFILE -E 'package(pageserver)'
# run pageserver tests with different settings
for io_engine in std-fs tokio-epoll-uring ; do
for io_buffer_alignment in 0 1 512 ; do
NEON_PAGESERVER_UNIT_TEST_VIRTUAL_FILE_IOENGINE=$io_engine NEON_PAGESERVER_UNIT_TEST_IO_BUFFER_ALIGNMENT=$io_buffer_alignment ${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_FEATURES -E 'package(pageserver)'
done
done
# Run separate tests for real S3
export ENABLE_REAL_S3_REMOTE_STORAGE=nonempty
export REMOTE_STORAGE_S3_BUCKET=neon-github-ci-tests
export REMOTE_STORAGE_S3_REGION=eu-central-1
${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_PROFILE -E 'package(remote_storage)' -E 'test(test_real_s3)'
${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_FEATURES -E 'package(remote_storage)' -E 'test(test_real_s3)'
# Run separate tests for real Azure Blob Storage
# XXX: replace region with `eu-central-1`-like region
@@ -293,46 +254,16 @@ jobs:
export AZURE_STORAGE_ACCESS_KEY="${{ secrets.AZURE_STORAGE_ACCESS_KEY_DEV }}"
export REMOTE_STORAGE_AZURE_CONTAINER="${{ vars.REMOTE_STORAGE_AZURE_CONTAINER }}"
export REMOTE_STORAGE_AZURE_REGION="${{ vars.REMOTE_STORAGE_AZURE_REGION }}"
${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_PROFILE -E 'package(remote_storage)' -E 'test(test_real_azure)'
${cov_prefix} cargo nextest run $CARGO_FLAGS $CARGO_FEATURES -E 'package(remote_storage)' -E 'test(test_real_azure)'
- name: Install postgres binaries
run: |
# Use tar to copy files matching the pattern, preserving the paths in the destionation
tar c \
pg_install/v* \
build/*/src/test/regress/*.so \
build/*/src/test/regress/pg_regress \
build/*/src/test/isolation/isolationtester \
build/*/src/test/isolation/pg_isolation_regress \
| tar x -C /tmp/neon
run: cp -a pg_install /tmp/neon/pg_install
- name: Upload Neon artifact
uses: ./.github/actions/upload
with:
name: neon-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}${{ inputs.sanitizers == 'enabled' && '-sanitized' || '' }}-artifact
name: neon-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-artifact
path: /tmp/neon
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Check diesel schema
if: inputs.build-type == 'release' && inputs.arch == 'x64'
env:
DATABASE_URL: postgresql://localhost:1235/storage_controller
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
run: |
export ASAN_OPTIONS=detect_leaks=0
/tmp/neon/bin/neon_local init
/tmp/neon/bin/neon_local storage_controller start
diesel print-schema > storage_controller/src/schema.rs
if [ -n "$(git diff storage_controller/src/schema.rs)" ]; then
echo >&2 "Uncommitted changes in diesel schema"
git diff .
exit 1
fi
/tmp/neon/bin/neon_local storage_controller stop
# XXX: keep this after the binaries.list is formed, so the coverage can properly work later
- name: Merge and upload coverage data
@@ -342,36 +273,27 @@ jobs:
regress-tests:
# Don't run regression tests on debug arm64 builds
if: inputs.build-type != 'debug' || inputs.arch != 'arm64'
permissions:
id-token: write # aws-actions/configure-aws-credentials
contents: read
statuses: write
needs: [ build-neon ]
runs-on: ${{ fromJSON(format('["self-hosted", "{0}"]', inputs.arch == 'arm64' && 'large-arm64' || 'large-metal')) }}
runs-on: ${{ fromJson(format('["self-hosted", "{0}"]', inputs.arch == 'arm64' && 'large-arm64' || 'large')) }}
container:
image: ${{ inputs.build-tools-image }}
credentials:
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
# for changed limits, see comments on `options:` earlier in this file
options: --init --shm-size=512mb --ulimit memlock=67108864:67108864
strategy:
fail-fast: false
matrix: ${{ fromJSON(format('{{"include":{0}}}', inputs.test-cfg)) }}
matrix:
pg_version: ${{ fromJson(inputs.pg-versions) }}
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- uses: actions/checkout@v4
with:
submodules: true
- name: Pytest regression tests
continue-on-error: ${{ matrix.lfc_state == 'with-lfc' && inputs.build-type == 'debug' }}
uses: ./.github/actions/run-python-test-set
timeout-minutes: ${{ (inputs.build-type == 'release' && inputs.sanitizers != 'enabled') && 75 || 180 }}
timeout-minutes: 60
with:
build_type: ${{ inputs.build-type }}
test_selection: regress
@@ -379,21 +301,13 @@ jobs:
run_with_real_s3: true
real_s3_bucket: neon-github-ci-tests
real_s3_region: eu-central-1
rerun_failed: ${{ inputs.rerun-failed }}
rerun_flaky: true
pg_version: ${{ matrix.pg_version }}
sanitizers: ${{ inputs.sanitizers }}
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
# `--session-timeout` is equal to (timeout-minutes - 10 minutes) * 60 seconds.
# Attempt to stop tests gracefully to generate test reports
# until they are forcibly stopped by the stricter `timeout-minutes` limit.
extra_params: --session-timeout=${{ (inputs.build-type == 'release' && inputs.sanitizers != 'enabled') && 3000 || 10200 }} --count=${{ inputs.test-run-count }}
${{ inputs.test-selection != '' && format('-k "{0}"', inputs.test-selection) || '' }}
env:
TEST_RESULT_CONNSTR: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
CHECK_ONDISK_DATA_COMPATIBILITY: nonempty
BUILD_TAG: ${{ inputs.build-tag }}
PAGESERVER_VIRTUAL_FILE_IO_ENGINE: tokio-epoll-uring
USE_LFC: ${{ matrix.lfc_state == 'with-lfc' && 'true' || 'false' }}
# Temporary disable this step until we figure out why it's so flaky
# Ref https://github.com/neondatabase/neon/issues/4540

View File

@@ -1,55 +0,0 @@
name: Check Codestyle Python
on:
workflow_call:
inputs:
build-tools-image:
description: 'build-tools image'
required: true
type: string
defaults:
run:
shell: bash -euxo pipefail {0}
permissions:
contents: read
jobs:
check-codestyle-python:
runs-on: [ self-hosted, small ]
permissions:
packages: read
container:
image: ${{ inputs.build-tools-image }}
credentials:
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Cache poetry deps
uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1 # v1.8.0
with:
endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
use-fallback: false
path: ~/.cache/pypoetry/virtualenvs
key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-bookworm-${{ hashFiles('poetry.lock') }}
- run: ./scripts/pysync
- run: poetry run ruff check .
- run: poetry run ruff format --check .
- run: poetry run mypy .

View File

@@ -1,106 +0,0 @@
name: Check Codestyle Rust
on:
workflow_call:
inputs:
build-tools-image:
description: "build-tools image"
required: true
type: string
archs:
description: "Json array of architectures to run on"
type: string
defaults:
run:
shell: bash -euxo pipefail {0}
# No permission for GITHUB_TOKEN by default; the **minimal required** set of permissions should be granted in each job.
permissions: {}
jobs:
check-codestyle-rust:
strategy:
matrix:
arch: ${{ fromJSON(inputs.archs) }}
runs-on: ${{ fromJSON(format('["self-hosted", "{0}"]', matrix.arch == 'arm64' && 'small-arm64' || 'small')) }}
permissions:
packages: read
container:
image: ${{ inputs.build-tools-image }}
credentials:
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Checkout
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
submodules: true
- uses: ./.github/actions/prepare-for-subzero
with:
token: ${{ secrets.CI_ACCESS_TOKEN }}
- name: Cache cargo deps
uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1 # v1.8.0
with:
endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
use-fallback: false
path: |
~/.cargo/registry
!~/.cargo/registry/src
~/.cargo/git
target
key: v1-${{ runner.os }}-${{ runner.arch }}-cargo-${{ hashFiles('./Cargo.lock') }}-${{ hashFiles('./rust-toolchain.toml') }}-rust
# Some of our rust modules use FFI and need those to be checked
- name: Get postgres headers
run: make postgres-headers -j$(nproc)
# cargo hack runs the given cargo subcommand (clippy in this case) for all feature combinations.
# This will catch compiler & clippy warnings in all feature combinations.
# TODO: use cargo hack for build and test as well, but, that's quite expensive.
# NB: keep clippy args in sync with ./run_clippy.sh
#
# The only difference between "clippy --debug" and "clippy --release" is that in --release mode,
# #[cfg(debug_assertions)] blocks are not built. It's not worth building everything for second
# time just for that, so skip "clippy --release".
- run: |
CLIPPY_COMMON_ARGS="$( source .neon_clippy_args; echo "$CLIPPY_COMMON_ARGS")"
if [ "$CLIPPY_COMMON_ARGS" = "" ]; then
echo "No clippy args found in .neon_clippy_args"
exit 1
fi
echo "CLIPPY_COMMON_ARGS=${CLIPPY_COMMON_ARGS}" >> $GITHUB_ENV
- name: Run cargo clippy (debug)
run: cargo hack --features default --ignore-unknown-features --feature-powerset clippy $CLIPPY_COMMON_ARGS
- name: Check documentation generation
run: cargo doc --workspace --no-deps --document-private-items
env:
RUSTDOCFLAGS: "-Dwarnings -Arustdoc::private_intra_doc_links"
# Use `${{ !cancelled() }}` to run quck tests after the longer clippy run
- name: Check formatting
if: ${{ !cancelled() }}
run: cargo fmt --all -- --check
# https://github.com/facebookincubator/cargo-guppy/tree/bec4e0eb29dcd1faac70b1b5360267fc02bf830e/tools/cargo-hakari#2-keep-the-workspace-hack-up-to-date-in-ci
- name: Check rust dependencies
if: ${{ !cancelled() }}
run: |
cargo hakari generate --diff # workspace-hack Cargo.toml is up-to-date
cargo hakari manage-deps --dry-run # all workspace crates depend on workspace-hack

View File

@@ -1,169 +0,0 @@
name: Generate run metadata
on:
workflow_call:
inputs:
github-event-name:
type: string
required: true
github-event-json:
type: string
required: true
outputs:
build-tag:
description: "Tag for the current workflow run"
value: ${{ jobs.tags.outputs.build-tag }}
release-tag:
description: "Tag for the release if this is an RC PR run"
value: ${{ jobs.tags.outputs.release-tag }}
previous-storage-release:
description: "Tag of the last storage release"
value: ${{ jobs.tags.outputs.storage }}
previous-proxy-release:
description: "Tag of the last proxy release"
value: ${{ jobs.tags.outputs.proxy }}
previous-compute-release:
description: "Tag of the last compute release"
value: ${{ jobs.tags.outputs.compute }}
run-kind:
description: "The kind of run we're currently in. Will be one of `push-main`, `storage-release`, `compute-release`, `proxy-release`, `storage-rc-pr`, `compute-rc-pr`, `proxy-rc-pr`, `pr`, or `workflow-dispatch`"
value: ${{ jobs.tags.outputs.run-kind }}
release-pr-run-id:
description: "Only available if `run-kind in [storage-release, proxy-release, compute-release]`. Contains the run ID of the `Build and Test` workflow, assuming one with the current commit can be found."
value: ${{ jobs.tags.outputs.release-pr-run-id }}
sha:
description: "github.event.pull_request.head.sha on release PRs, github.sha otherwise"
value: ${{ jobs.tags.outputs.sha }}
permissions: {}
defaults:
run:
shell: bash -euo pipefail {0}
jobs:
tags:
runs-on: ubuntu-22.04
outputs:
build-tag: ${{ steps.build-tag.outputs.build-tag }}
release-tag: ${{ steps.build-tag.outputs.release-tag }}
compute: ${{ steps.previous-releases.outputs.compute }}
proxy: ${{ steps.previous-releases.outputs.proxy }}
storage: ${{ steps.previous-releases.outputs.storage }}
run-kind: ${{ steps.run-kind.outputs.run-kind }}
release-pr-run-id: ${{ steps.release-pr-run-id.outputs.release-pr-run-id }}
sha: ${{ steps.sha.outputs.sha }}
permissions:
contents: read
steps:
# Need `fetch-depth: 0` to count the number of commits in the branch
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Get run kind
id: run-kind
env:
RUN_KIND: >-
${{
false
|| (inputs.github-event-name == 'push' && github.ref_name == 'main') && 'push-main'
|| (inputs.github-event-name == 'push' && github.ref_name == 'release') && 'storage-release'
|| (inputs.github-event-name == 'push' && github.ref_name == 'release-compute') && 'compute-release'
|| (inputs.github-event-name == 'push' && github.ref_name == 'release-proxy') && 'proxy-release'
|| (inputs.github-event-name == 'pull_request' && github.base_ref == 'release') && 'storage-rc-pr'
|| (inputs.github-event-name == 'pull_request' && github.base_ref == 'release-compute') && 'compute-rc-pr'
|| (inputs.github-event-name == 'pull_request' && github.base_ref == 'release-proxy') && 'proxy-rc-pr'
|| (inputs.github-event-name == 'pull_request') && 'pr'
|| (inputs.github-event-name == 'workflow_dispatch') && 'workflow-dispatch'
|| 'unknown'
}}
run: |
echo "run-kind=$RUN_KIND" | tee -a $GITHUB_OUTPUT
- name: Get the right SHA
id: sha
env:
SHA: >
${{
contains(fromJSON('["storage-rc-pr", "proxy-rc-pr", "compute-rc-pr"]'), steps.run-kind.outputs.run-kind)
&& fromJSON(inputs.github-event-json).pull_request.head.sha
|| github.sha
}}
run: |
echo "sha=$SHA" | tee -a $GITHUB_OUTPUT
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
fetch-depth: 0
ref: ${{ steps.sha.outputs.sha }}
- name: Get build tag
id: build-tag
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
CURRENT_BRANCH: ${{ github.head_ref || github.ref_name }}
CURRENT_SHA: ${{ github.event.pull_request.head.sha || github.sha }}
RUN_KIND: ${{ steps.run-kind.outputs.run-kind }}
run: |
case $RUN_KIND in
push-main)
echo "build-tag=$(git rev-list --count HEAD)" | tee -a $GITHUB_OUTPUT
;;
storage-release)
echo "build-tag=release-$(git rev-list --count HEAD)" | tee -a $GITHUB_OUTPUT
;;
proxy-release)
echo "build-tag=release-proxy-$(git rev-list --count HEAD)" | tee -a $GITHUB_OUTPUT
;;
compute-release)
echo "build-tag=release-compute-$(git rev-list --count HEAD)" | tee -a $GITHUB_OUTPUT
;;
pr|storage-rc-pr|compute-rc-pr|proxy-rc-pr)
BUILD_AND_TEST_RUN_ID=$(gh api --paginate \
-H "Accept: application/vnd.github+json" \
-H "X-GitHub-Api-Version: 2022-11-28" \
"/repos/${GITHUB_REPOSITORY}/actions/runs?head_sha=${CURRENT_SHA}&branch=${CURRENT_BRANCH}" \
| jq '[.workflow_runs[] | select(.name == "Build and Test")][0].id // ("Error: No matching workflow run found." | halt_error(1))')
echo "build-tag=$BUILD_AND_TEST_RUN_ID" | tee -a $GITHUB_OUTPUT
case $RUN_KIND in
storage-rc-pr)
echo "release-tag=release-$(git rev-list --count HEAD)" | tee -a $GITHUB_OUTPUT
;;
proxy-rc-pr)
echo "release-tag=release-proxy-$(git rev-list --count HEAD)" | tee -a $GITHUB_OUTPUT
;;
compute-rc-pr)
echo "release-tag=release-compute-$(git rev-list --count HEAD)" | tee -a $GITHUB_OUTPUT
;;
esac
;;
workflow-dispatch)
echo "build-tag=$GITHUB_RUN_ID" | tee -a $GITHUB_OUTPUT
;;
*)
echo "Unexpected RUN_KIND ('${RUN_KIND}'), failing to assign build-tag!"
exit 1
esac
- name: Get the previous release-tags
id: previous-releases
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
gh api --paginate \
-H "Accept: application/vnd.github+json" \
-H "X-GitHub-Api-Version: 2022-11-28" \
"/repos/${GITHUB_REPOSITORY}/releases" \
| jq -f .github/scripts/previous-releases.jq -r \
| tee -a "${GITHUB_OUTPUT}"
- name: Get the release PR run ID
id: release-pr-run-id
if: ${{ contains(fromJSON('["storage-release", "compute-release", "proxy-release"]'), steps.run-kind.outputs.run-kind) }}
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
CURRENT_SHA: ${{ github.sha }}
run: |
RELEASE_PR_RUN_ID=$(gh api "/repos/${GITHUB_REPOSITORY}/actions/runs?head_sha=$CURRENT_SHA" | jq '[.workflow_runs[] | select(.name == "Build and Test") | select(.head_branch | test("^rc/release.*$"; "s"))] | first | .id // ("Failed to find Build and Test run from RC PR!" | halt_error(1))')
echo "release-pr-run-id=$RELEASE_PR_RUN_ID" | tee -a $GITHUB_OUTPUT

56
.github/workflows/_push-to-acr.yml vendored Normal file
View File

@@ -0,0 +1,56 @@
name: Push images to ACR
on:
workflow_call:
inputs:
client_id:
description: Client ID of Azure managed identity or Entra app
required: true
type: string
image_tag:
description: Tag for the container image
required: true
type: string
images:
description: Images to push
required: true
type: string
registry_name:
description: Name of the container registry
required: true
type: string
subscription_id:
description: Azure subscription ID
required: true
type: string
tenant_id:
description: Azure tenant ID
required: true
type: string
jobs:
push-to-acr:
runs-on: ubuntu-22.04
permissions:
contents: read # This is required for actions/checkout
id-token: write # This is required for Azure Login to work.
steps:
- name: Azure login
uses: azure/login@6c251865b4e6290e7b78be643ea2d005bc51f69a # @v2.1.1
with:
client-id: ${{ inputs.client_id }}
subscription-id: ${{ inputs.subscription_id }}
tenant-id: ${{ inputs.tenant_id }}
- name: Login to ACR
run: |
az acr login --name=${{ inputs.registry_name }}
- name: Copy docker images to ACR ${{ inputs.registry_name }}
run: |
images='${{ inputs.images }}'
for image in ${images}; do
docker buildx imagetools create \
-t ${{ inputs.registry_name }}.azurecr.io/neondatabase/${image}:${{ inputs.image_tag }} \
neondatabase/${image}:${{ inputs.image_tag }}
done

View File

@@ -1,128 +0,0 @@
name: Push images to Container Registry
on:
workflow_call:
inputs:
# Example: {"docker.io/neondatabase/neon:13196061314":["${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}.dkr.ecr.${{ vars.AWS_ECR_REGION }}.amazonaws.com/neon:13196061314","neoneastus2.azurecr.io/neondatabase/neon:13196061314"]}
image-map:
description: JSON map of images, mapping from a source image to an array of target images that should be pushed.
required: true
type: string
aws-region:
description: AWS region to log in to. Required when pushing to ECR.
required: false
type: string
aws-account-id:
description: AWS account ID to log in to for pushing to ECR. Required when pushing to ECR.
required: false
type: string
aws-role-to-assume:
description: AWS role to assume to for pushing to ECR. Required when pushing to ECR.
required: false
type: string
azure-client-id:
description: Client ID of Azure managed identity or Entra app. Required when pushing to ACR.
required: false
type: string
azure-subscription-id:
description: Azure subscription ID. Required when pushing to ACR.
required: false
type: string
azure-tenant-id:
description: Azure tenant ID. Required when pushing to ACR.
required: false
type: string
acr-registry-name:
description: ACR registry name. Required when pushing to ACR.
required: false
type: string
permissions: {}
defaults:
run:
shell: bash -euo pipefail {0}
jobs:
push-to-container-registry:
runs-on: ubuntu-22.04
permissions:
id-token: write # Required for aws/azure login
packages: write # required for pushing to GHCR
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
sparse-checkout: .github/scripts/push_with_image_map.py
sparse-checkout-cone-mode: false
- name: Print image-map
run: echo '${{ inputs.image-map }}' | jq
- name: Configure AWS credentials
if: contains(inputs.image-map, 'amazonaws.com/')
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: "${{ inputs.aws-region }}"
role-to-assume: "arn:aws:iam::${{ inputs.aws-account-id }}:role/${{ inputs.aws-role-to-assume }}"
role-duration-seconds: 3600
- name: Login to ECR
if: contains(inputs.image-map, 'amazonaws.com/')
uses: aws-actions/amazon-ecr-login@062b18b96a7aff071d4dc91bc00c4c1a7945b076 # v2.0.1
with:
registries: "${{ inputs.aws-account-id }}"
- name: Configure Azure credentials
if: contains(inputs.image-map, 'azurecr.io/')
uses: azure/login@6c251865b4e6290e7b78be643ea2d005bc51f69a # @v2.1.1
with:
client-id: ${{ inputs.azure-client-id }}
subscription-id: ${{ inputs.azure-subscription-id }}
tenant-id: ${{ inputs.azure-tenant-id }}
- name: Login to ACR
if: contains(inputs.image-map, 'azurecr.io/')
run: |
az acr login --name=${{ inputs.acr-registry-name }}
- name: Login to GHCR
if: contains(inputs.image-map, 'ghcr.io/')
uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Log in to Docker Hub
uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
- name: Copy docker images to target registries
id: push
run: python3 .github/scripts/push_with_image_map.py
env:
IMAGE_MAP: ${{ inputs.image-map }}
- name: Notify Slack if container image pushing fails
if: steps.push.outputs.push_failures || failure()
uses: slackapi/slack-github-action@485a9d42d3a73031f12ec201c457e2162c45d02d # v2.0.0
with:
method: chat.postMessage
token: ${{ secrets.SLACK_BOT_TOKEN }}
payload: |
channel: ${{ vars.SLACK_ON_CALL_DEVPROD_STREAM }}
text: >
*Container image pushing ${{
steps.push.outcome == 'failure' && 'failed completely' || 'succeeded with some retries'
}}* in
<${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}|GitHub Run>
${{ steps.push.outputs.push_failures && format(
'*Failed targets:*\n• {0}', join(fromJson(steps.push.outputs.push_failures), '\n• ')
) || '' }}

View File

@@ -26,19 +26,14 @@ jobs:
needs: [ check-permissions ]
runs-on: ubuntu-22.04
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- uses: reviewdog/action-actionlint@a5524e1c19e62881d79c1f1b9b6f09f16356e281 # v1.65.2
- uses: actions/checkout@v4
- uses: reviewdog/action-actionlint@v1
env:
# SC2046 - Quote this to prevent word splitting. - https://www.shellcheck.net/wiki/SC2046
# SC2086 - Double quote to prevent globbing and word splitting. - https://www.shellcheck.net/wiki/SC2086
SHELLCHECK_OPTS: --exclude=SC2046,SC2086
with:
fail_level: error
fail_on_error: true
filter_mode: nofilter
level: error

View File

@@ -47,11 +47,6 @@ jobs:
runs-on: ubuntu-22.04
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- run: gh pr --repo "${GITHUB_REPOSITORY}" edit "${PR_NUMBER}" --remove-label "approved-for-ci-run"
create-or-update-pr-for-ci-run:
@@ -68,18 +63,13 @@ jobs:
runs-on: ubuntu-22.04
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- run: gh pr --repo "${GITHUB_REPOSITORY}" edit "${PR_NUMBER}" --remove-label "approved-for-ci-run"
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- uses: actions/checkout@v4
with:
ref: ${{ github.event.pull_request.head.sha }}
ref: main
token: ${{ secrets.CI_ACCESS_TOKEN }}
- name: Look for existing PR
id: get-pr
env:
@@ -87,7 +77,7 @@ jobs:
run: |
ALREADY_CREATED="$(gh pr --repo ${GITHUB_REPOSITORY} list --head ${BRANCH} --base main --json number --jq '.[].number')"
echo "ALREADY_CREATED=${ALREADY_CREATED}" >> ${GITHUB_OUTPUT}
- name: Get changed labels
id: get-labels
if: steps.get-pr.outputs.ALREADY_CREATED != ''
@@ -104,6 +94,8 @@ jobs:
echo "LABELS_TO_ADD=${LABELS_TO_ADD}" >> ${GITHUB_OUTPUT}
echo "LABELS_TO_REMOVE=${LABELS_TO_REMOVE}" >> ${GITHUB_OUTPUT}
- run: gh pr checkout "${PR_NUMBER}"
- run: git checkout -b "${BRANCH}"
- run: git push --force origin "${BRANCH}"
@@ -111,7 +103,7 @@ jobs:
- name: Create a Pull Request for CI run (if required)
if: steps.get-pr.outputs.ALREADY_CREATED == ''
env:
env:
GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
run: |
cat << EOF > body.md
@@ -148,7 +140,7 @@ jobs:
- run: git push --force origin "${BRANCH}"
if: steps.get-pr.outputs.ALREADY_CREATED != ''
cleanup:
# Close PRs and delete branchs if the original PR is closed.
@@ -163,11 +155,6 @@ jobs:
runs-on: ubuntu-22.04
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Close PR and delete `ci-run/pr-${{ env.PR_NUMBER }}` branch
run: |
CLOSED="$(gh pr --repo ${GITHUB_REPOSITORY} list --head ${BRANCH} --json 'closed' --jq '.[].closed')"

View File

@@ -1,384 +0,0 @@
name: TPC-C like benchmark using benchbase
on:
schedule:
# * is a special character in YAML so you have to quote this string
# ┌───────────── minute (0 - 59)
# │ ┌───────────── hour (0 - 23)
# │ │ ┌───────────── day of the month (1 - 31)
# │ │ │ ┌───────────── month (1 - 12 or JAN-DEC)
# │ │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
- cron: '0 6 * * *' # run once a day at 6 AM UTC
workflow_dispatch: # adds ability to run this manually
defaults:
run:
shell: bash -euxo pipefail {0}
concurrency:
# Allow only one workflow globally because we do not want to be too noisy in production environment
group: benchbase-tpcc-workflow
cancel-in-progress: false
permissions:
contents: read
jobs:
benchbase-tpcc:
strategy:
fail-fast: false # allow other variants to continue even if one fails
matrix:
include:
- warehouses: 50 # defines number of warehouses and is used to compute number of terminals
max_rate: 800 # measured max TPS at scale factor based on experiments. Adjust if performance is better/worse
min_cu: 0.25 # simulate free tier plan (0.25 -2 CU)
max_cu: 2
- warehouses: 500 # serverless plan (2-8 CU)
max_rate: 2000
min_cu: 2
max_cu: 8
- warehouses: 1000 # business plan (2-16 CU)
max_rate: 2900
min_cu: 2
max_cu: 16
max-parallel: 1 # we want to run each workload size sequentially to avoid noisy neighbors
permissions:
contents: write
statuses: write
id-token: write # aws-actions/configure-aws-credentials
env:
PG_CONFIG: /tmp/neon/pg_install/v17/bin/pg_config
PSQL: /tmp/neon/pg_install/v17/bin/psql
PG_17_LIB_PATH: /tmp/neon/pg_install/v17/lib
POSTGRES_VERSION: 17
runs-on: [ self-hosted, us-east-2, x64 ]
timeout-minutes: 1440
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Configure AWS credentials # necessary to download artefacts
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 18000 # 5 hours is currently max associated with IAM role
- name: Download Neon artifact
uses: ./.github/actions/download
with:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Create Neon Project
id: create-neon-project-tpcc
uses: ./.github/actions/neon-project-create
with:
region_id: aws-us-east-2
postgres_version: ${{ env.POSTGRES_VERSION }}
compute_units: '[${{ matrix.min_cu }}, ${{ matrix.max_cu }}]'
api_key: ${{ secrets.NEON_PRODUCTION_API_KEY_4_BENCHMARKS }}
api_host: console.neon.tech # production (!)
- name: Initialize Neon project
env:
BENCHMARK_TPCC_CONNSTR: ${{ steps.create-neon-project-tpcc.outputs.dsn }}
PROJECT_ID: ${{ steps.create-neon-project-tpcc.outputs.project_id }}
run: |
echo "Initializing Neon project with project_id: ${PROJECT_ID}"
export LD_LIBRARY_PATH=${PG_17_LIB_PATH}
# Retry logic for psql connection with 1 minute sleep between attempts
for attempt in {1..3}; do
echo "Attempt ${attempt}/3: Creating extensions in Neon project"
if ${PSQL} "${BENCHMARK_TPCC_CONNSTR}" -c "CREATE EXTENSION IF NOT EXISTS neon; CREATE EXTENSION IF NOT EXISTS neon_utils;"; then
echo "Successfully created extensions"
break
else
echo "Failed to create extensions on attempt ${attempt}"
if [ ${attempt} -lt 3 ]; then
echo "Waiting 60 seconds before retry..."
sleep 60
else
echo "All attempts failed, exiting"
exit 1
fi
fi
done
echo "BENCHMARK_TPCC_CONNSTR=${BENCHMARK_TPCC_CONNSTR}" >> $GITHUB_ENV
- name: Generate BenchBase workload configuration
env:
WAREHOUSES: ${{ matrix.warehouses }}
MAX_RATE: ${{ matrix.max_rate }}
run: |
echo "Generating BenchBase configs for warehouses: ${WAREHOUSES}, max_rate: ${MAX_RATE}"
# Extract hostname and password from connection string
# Format: postgresql://username:password@hostname/database?params (no port for Neon)
HOSTNAME=$(echo "${BENCHMARK_TPCC_CONNSTR}" | sed -n 's|.*://[^:]*:[^@]*@\([^/]*\)/.*|\1|p')
PASSWORD=$(echo "${BENCHMARK_TPCC_CONNSTR}" | sed -n 's|.*://[^:]*:\([^@]*\)@.*|\1|p')
echo "Extracted hostname: ${HOSTNAME}"
# Use runner temp (NVMe) as working directory
cd "${RUNNER_TEMP}"
# Copy the generator script
cp "${GITHUB_WORKSPACE}/test_runner/performance/benchbase_tpc_c_helpers/generate_workload_size.py" .
# Generate configs and scripts
python3 generate_workload_size.py \
--warehouses ${WAREHOUSES} \
--max-rate ${MAX_RATE} \
--hostname ${HOSTNAME} \
--password ${PASSWORD} \
--runner-arch ${{ runner.arch }}
# Fix path mismatch: move generated configs and scripts to expected locations
mv ../configs ./configs
mv ../scripts ./scripts
- name: Prepare database (load data)
env:
WAREHOUSES: ${{ matrix.warehouses }}
run: |
cd "${RUNNER_TEMP}"
echo "Loading ${WAREHOUSES} warehouses into database..."
# Run the loader script and capture output to log file while preserving stdout/stderr
./scripts/load_${WAREHOUSES}_warehouses.sh 2>&1 | tee "load_${WAREHOUSES}_warehouses.log"
echo "Database loading completed"
- name: Run TPC-C benchmark (warmup phase, then benchmark at 70% of configuredmax TPS)
env:
WAREHOUSES: ${{ matrix.warehouses }}
run: |
cd "${RUNNER_TEMP}"
echo "Running TPC-C benchmark with ${WAREHOUSES} warehouses..."
# Run the optimal rate benchmark
./scripts/execute_${WAREHOUSES}_warehouses_opt_rate.sh
echo "Benchmark execution completed"
- name: Run TPC-C benchmark (warmup phase, then ramp down TPS and up again in 5 minute intervals)
env:
WAREHOUSES: ${{ matrix.warehouses }}
run: |
cd "${RUNNER_TEMP}"
echo "Running TPC-C ramp-down-up with ${WAREHOUSES} warehouses..."
# Run the optimal rate benchmark
./scripts/execute_${WAREHOUSES}_warehouses_ramp_up.sh
echo "Benchmark execution completed"
- name: Process results (upload to test results database and generate diagrams)
env:
WAREHOUSES: ${{ matrix.warehouses }}
MIN_CU: ${{ matrix.min_cu }}
MAX_CU: ${{ matrix.max_cu }}
PROJECT_ID: ${{ steps.create-neon-project-tpcc.outputs.project_id }}
REVISION: ${{ github.sha }}
PERF_DB_CONNSTR: ${{ secrets.PERF_TEST_RESULT_CONNSTR }}
run: |
cd "${RUNNER_TEMP}"
echo "Creating temporary Python environment for results processing..."
# Create temporary virtual environment
python3 -m venv temp_results_env
source temp_results_env/bin/activate
# Install required packages in virtual environment
pip install matplotlib pandas psycopg2-binary
echo "Copying results processing scripts..."
# Copy both processing scripts
cp "${GITHUB_WORKSPACE}/test_runner/performance/benchbase_tpc_c_helpers/generate_diagrams.py" .
cp "${GITHUB_WORKSPACE}/test_runner/performance/benchbase_tpc_c_helpers/upload_results_to_perf_test_results.py" .
echo "Processing load phase metrics..."
# Find and process load log
LOAD_LOG=$(find . -name "load_${WAREHOUSES}_warehouses.log" -type f | head -1)
if [ -n "$LOAD_LOG" ]; then
echo "Processing load metrics from: $LOAD_LOG"
python upload_results_to_perf_test_results.py \
--load-log "$LOAD_LOG" \
--run-type "load" \
--warehouses "${WAREHOUSES}" \
--min-cu "${MIN_CU}" \
--max-cu "${MAX_CU}" \
--project-id "${PROJECT_ID}" \
--revision "${REVISION}" \
--connection-string "${PERF_DB_CONNSTR}"
else
echo "Warning: Load log file not found: load_${WAREHOUSES}_warehouses.log"
fi
echo "Processing warmup results for optimal rate..."
# Find and process warmup results
WARMUP_CSV=$(find results_warmup -name "*.results.csv" -type f | head -1)
WARMUP_JSON=$(find results_warmup -name "*.summary.json" -type f | head -1)
if [ -n "$WARMUP_CSV" ] && [ -n "$WARMUP_JSON" ]; then
echo "Generating warmup diagram from: $WARMUP_CSV"
python generate_diagrams.py \
--input-csv "$WARMUP_CSV" \
--output-svg "warmup_${WAREHOUSES}_warehouses_performance.svg" \
--title-suffix "Warmup at max TPS"
echo "Uploading warmup metrics from: $WARMUP_JSON"
python upload_results_to_perf_test_results.py \
--summary-json "$WARMUP_JSON" \
--results-csv "$WARMUP_CSV" \
--run-type "warmup" \
--min-cu "${MIN_CU}" \
--max-cu "${MAX_CU}" \
--project-id "${PROJECT_ID}" \
--revision "${REVISION}" \
--connection-string "${PERF_DB_CONNSTR}"
else
echo "Warning: Missing warmup results files (CSV: $WARMUP_CSV, JSON: $WARMUP_JSON)"
fi
echo "Processing optimal rate results..."
# Find and process optimal rate results
OPTRATE_CSV=$(find results_opt_rate -name "*.results.csv" -type f | head -1)
OPTRATE_JSON=$(find results_opt_rate -name "*.summary.json" -type f | head -1)
if [ -n "$OPTRATE_CSV" ] && [ -n "$OPTRATE_JSON" ]; then
echo "Generating optimal rate diagram from: $OPTRATE_CSV"
python generate_diagrams.py \
--input-csv "$OPTRATE_CSV" \
--output-svg "benchmark_${WAREHOUSES}_warehouses_performance.svg" \
--title-suffix "70% of max TPS"
echo "Uploading optimal rate metrics from: $OPTRATE_JSON"
python upload_results_to_perf_test_results.py \
--summary-json "$OPTRATE_JSON" \
--results-csv "$OPTRATE_CSV" \
--run-type "opt-rate" \
--min-cu "${MIN_CU}" \
--max-cu "${MAX_CU}" \
--project-id "${PROJECT_ID}" \
--revision "${REVISION}" \
--connection-string "${PERF_DB_CONNSTR}"
else
echo "Warning: Missing optimal rate results files (CSV: $OPTRATE_CSV, JSON: $OPTRATE_JSON)"
fi
echo "Processing warmup 2 results for ramp down/up phase..."
# Find and process warmup results
WARMUP_CSV=$(find results_warmup -name "*.results.csv" -type f | tail -1)
WARMUP_JSON=$(find results_warmup -name "*.summary.json" -type f | tail -1)
if [ -n "$WARMUP_CSV" ] && [ -n "$WARMUP_JSON" ]; then
echo "Generating warmup diagram from: $WARMUP_CSV"
python generate_diagrams.py \
--input-csv "$WARMUP_CSV" \
--output-svg "warmup_2_${WAREHOUSES}_warehouses_performance.svg" \
--title-suffix "Warmup at max TPS"
echo "Uploading warmup metrics from: $WARMUP_JSON"
python upload_results_to_perf_test_results.py \
--summary-json "$WARMUP_JSON" \
--results-csv "$WARMUP_CSV" \
--run-type "warmup" \
--min-cu "${MIN_CU}" \
--max-cu "${MAX_CU}" \
--project-id "${PROJECT_ID}" \
--revision "${REVISION}" \
--connection-string "${PERF_DB_CONNSTR}"
else
echo "Warning: Missing warmup results files (CSV: $WARMUP_CSV, JSON: $WARMUP_JSON)"
fi
echo "Processing ramp results..."
# Find and process ramp results
RAMPUP_CSV=$(find results_ramp_up -name "*.results.csv" -type f | head -1)
RAMPUP_JSON=$(find results_ramp_up -name "*.summary.json" -type f | head -1)
if [ -n "$RAMPUP_CSV" ] && [ -n "$RAMPUP_JSON" ]; then
echo "Generating ramp diagram from: $RAMPUP_CSV"
python generate_diagrams.py \
--input-csv "$RAMPUP_CSV" \
--output-svg "ramp_${WAREHOUSES}_warehouses_performance.svg" \
--title-suffix "ramp TPS down and up in 5 minute intervals"
echo "Uploading ramp metrics from: $RAMPUP_JSON"
python upload_results_to_perf_test_results.py \
--summary-json "$RAMPUP_JSON" \
--results-csv "$RAMPUP_CSV" \
--run-type "ramp-up" \
--min-cu "${MIN_CU}" \
--max-cu "${MAX_CU}" \
--project-id "${PROJECT_ID}" \
--revision "${REVISION}" \
--connection-string "${PERF_DB_CONNSTR}"
else
echo "Warning: Missing ramp results files (CSV: $RAMPUP_CSV, JSON: $RAMPUP_JSON)"
fi
# Deactivate and clean up virtual environment
deactivate
rm -rf temp_results_env
rm upload_results_to_perf_test_results.py
echo "Results processing completed and environment cleaned up"
- name: Set date for upload
id: set-date
run: echo "date=$(date +%Y-%m-%d)" >> $GITHUB_OUTPUT
- name: Configure AWS credentials # necessary to upload results
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: us-east-2
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 900 # 900 is minimum value
- name: Upload benchmark results to S3
env:
S3_BUCKET: neon-public-benchmark-results
S3_PREFIX: benchbase-tpc-c/${{ steps.set-date.outputs.date }}/${{ github.run_id }}/${{ matrix.warehouses }}-warehouses
run: |
echo "Redacting passwords from configuration files before upload..."
# Mask all passwords in XML config files
find "${RUNNER_TEMP}/configs" -name "*.xml" -type f -exec sed -i 's|<password>[^<]*</password>|<password>redacted</password>|g' {} \;
echo "Uploading benchmark results to s3://${S3_BUCKET}/${S3_PREFIX}/"
# Upload the entire benchmark directory recursively
aws s3 cp --only-show-errors --recursive "${RUNNER_TEMP}" s3://${S3_BUCKET}/${S3_PREFIX}/
echo "Upload completed"
- name: Delete Neon Project
if: ${{ always() }}
uses: ./.github/actions/neon-project-delete
with:
project_id: ${{ steps.create-neon-project-tpcc.outputs.project_id }}
api_key: ${{ secrets.NEON_PRODUCTION_API_KEY_4_BENCHMARKS }}
api_host: console.neon.tech # production (!)

File diff suppressed because it is too large Load Diff

View File

@@ -3,100 +3,32 @@ name: Build build-tools image
on:
workflow_call:
inputs:
archs:
description: "Json array of architectures to build"
# Default values are set in `check-image` job, `set-variables` step
image-tag:
description: "build-tools image tag"
required: true
type: string
required: false
debians:
description: "Json array of Debian versions to build"
# Default values are set in `check-image` job, `set-variables` step
type: string
required: false
outputs:
image-tag:
description: "build-tools tag"
value: ${{ jobs.check-image.outputs.tag }}
value: ${{ inputs.image-tag }}
image:
description: "build-tools image"
value: ghcr.io/neondatabase/build-tools:${{ jobs.check-image.outputs.tag }}
value: neondatabase/build-tools:${{ inputs.image-tag }}
defaults:
run:
shell: bash -euo pipefail {0}
# The initial idea was to prevent the waste of resources by not re-building the `build-tools` image
# for the same tag in parallel workflow runs, and queue them to be skipped once we have
# the first image pushed to Docker registry, but GitHub's concurrency mechanism is not working as expected.
# GitHub can't have more than 1 job in a queue and removes the previous one, it causes failures if the dependent jobs.
#
# Ref https://github.com/orgs/community/discussions/41518
#
# concurrency:
# group: build-build-tools-image-${{ inputs.image-tag }}
# cancel-in-progress: false
concurrency:
group: build-build-tools-image-${{ inputs.image-tag }}
cancel-in-progress: false
# No permission for GITHUB_TOKEN by default; the **minimal required** set of permissions should be granted in each job.
permissions: {}
jobs:
check-image:
runs-on: ubuntu-22.04
outputs:
archs: ${{ steps.set-variables.outputs.archs }}
debians: ${{ steps.set-variables.outputs.debians }}
tag: ${{ steps.set-variables.outputs.image-tag }}
everything: ${{ steps.set-more-variables.outputs.everything }}
found: ${{ steps.set-more-variables.outputs.found }}
permissions:
packages: read
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Set variables
id: set-variables
env:
ARCHS: ${{ inputs.archs || '["x64","arm64"]' }}
DEBIANS: ${{ inputs.debians || '["bullseye","bookworm"]' }}
IMAGE_TAG: |
${{ hashFiles('build-tools/Dockerfile',
'.github/workflows/build-build-tools-image.yml') }}
run: |
echo "archs=${ARCHS}" | tee -a ${GITHUB_OUTPUT}
echo "debians=${DEBIANS}" | tee -a ${GITHUB_OUTPUT}
echo "image-tag=${IMAGE_TAG}" | tee -a ${GITHUB_OUTPUT}
- name: Set more variables
id: set-more-variables
env:
IMAGE_TAG: ${{ steps.set-variables.outputs.image-tag }}
EVERYTHING: |
${{ contains(fromJSON(steps.set-variables.outputs.archs), 'x64') &&
contains(fromJSON(steps.set-variables.outputs.archs), 'arm64') &&
contains(fromJSON(steps.set-variables.outputs.debians), 'bullseye') &&
contains(fromJSON(steps.set-variables.outputs.debians), 'bookworm') }}
run: |
if docker manifest inspect ghcr.io/neondatabase/build-tools:${IMAGE_TAG}; then
found=true
else
found=false
fi
echo "everything=${EVERYTHING}" | tee -a ${GITHUB_OUTPUT}
echo "found=${found}" | tee -a ${GITHUB_OUTPUT}
uses: ./.github/workflows/check-build-tools-image.yml
build-image:
needs: [ check-image ]
@@ -104,100 +36,68 @@ jobs:
strategy:
matrix:
arch: ${{ fromJSON(needs.check-image.outputs.archs) }}
debian: ${{ fromJSON(needs.check-image.outputs.debians) }}
arch: [ x64, arm64 ]
permissions:
packages: write
runs-on: ${{ fromJson(format('["self-hosted", "{0}"]', matrix.arch == 'arm64' && 'large-arm64' || 'large')) }}
runs-on: ${{ fromJSON(format('["self-hosted", "{0}"]', matrix.arch == 'arm64' && 'large-arm64' || 'large')) }}
env:
IMAGE_TAG: ${{ inputs.image-tag }}
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Check `input.tag` is correct
env:
INPUTS_IMAGE_TAG: ${{ inputs.image-tag }}
CHECK_IMAGE_TAG : ${{ needs.check-image.outputs.image-tag }}
run: |
if [ "${INPUTS_IMAGE_TAG}" != "${CHECK_IMAGE_TAG}" ]; then
echo "'inputs.image-tag' (${INPUTS_IMAGE_TAG}) does not match the tag of the latest build-tools image 'inputs.image-tag' (${CHECK_IMAGE_TAG})"
exit 1
fi
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- uses: actions/checkout@v4
- uses: neondatabase/dev-actions/set-docker-config-dir@6094485bf440001c94a94a3f9e221e81ff6b6193
- uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
- uses: ./.github/actions/set-docker-config-dir
- uses: docker/setup-buildx-action@v3
with:
cache-binary: false
- uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
- uses: docker/login-action@v3
with:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
- uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
- uses: docker/login-action@v3
with:
registry: cache.neon.build
username: ${{ secrets.NEON_CI_DOCKERCACHE_USERNAME }}
password: ${{ secrets.NEON_CI_DOCKERCACHE_PASSWORD }}
- uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
- uses: docker/build-push-action@v6
with:
file: build-tools/Dockerfile
context: .
provenance: false
push: true
pull: true
build-args: |
DEBIAN_VERSION=${{ matrix.debian }}
cache-from: type=registry,ref=cache.neon.build/build-tools:cache-${{ matrix.debian }}-${{ matrix.arch }}
cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/build-tools:cache-{0}-{1},mode=max', matrix.debian, matrix.arch) || '' }}
tags: |
ghcr.io/neondatabase/build-tools:${{ needs.check-image.outputs.tag }}-${{ matrix.debian }}-${{ matrix.arch }}
file: Dockerfile.build-tools
cache-from: type=registry,ref=cache.neon.build/build-tools:cache-${{ matrix.arch }}
cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/build-tools:cache-{0},mode=max', matrix.arch) || '' }}
tags: neondatabase/build-tools:${{ inputs.image-tag }}-${{ matrix.arch }}
merge-images:
needs: [ check-image, build-image ]
needs: [ build-image ]
runs-on: ubuntu-22.04
permissions:
packages: write
env:
IMAGE_TAG: ${{ inputs.image-tag }}
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
- uses: docker/login-action@v3
with:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
- uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Create multi-arch image
env:
DEFAULT_DEBIAN_VERSION: bookworm
ARCHS: ${{ join(fromJSON(needs.check-image.outputs.archs), ' ') }}
DEBIANS: ${{ join(fromJSON(needs.check-image.outputs.debians), ' ') }}
EVERYTHING: ${{ needs.check-image.outputs.everything }}
IMAGE_TAG: ${{ needs.check-image.outputs.tag }}
run: |
for debian in ${DEBIANS}; do
tags=("-t" "ghcr.io/neondatabase/build-tools:${IMAGE_TAG}-${debian}")
if [ "${EVERYTHING}" == "true" ] && [ "${debian}" == "${DEFAULT_DEBIAN_VERSION}" ]; then
tags+=("-t" "ghcr.io/neondatabase/build-tools:${IMAGE_TAG}")
fi
for arch in ${ARCHS}; do
tags+=("ghcr.io/neondatabase/build-tools:${IMAGE_TAG}-${debian}-${arch}")
done
docker buildx imagetools create "${tags[@]}"
done
docker buildx imagetools create -t neondatabase/build-tools:${IMAGE_TAG} \
neondatabase/build-tools:${IMAGE_TAG}-x64 \
neondatabase/build-tools:${IMAGE_TAG}-arm64

View File

@@ -1,128 +0,0 @@
name: Check neon with MacOS builds
on:
workflow_call:
inputs:
pg_versions:
description: "Array of the pg versions to build for, for example: ['v14', 'v17']"
type: string
default: '[]'
required: false
rebuild_rust_code:
description: "Rebuild Rust code"
type: boolean
default: false
required: false
rebuild_everything:
description: "If true, rebuild for all versions"
type: boolean
default: false
required: false
env:
RUST_BACKTRACE: 1
COPT: '-Werror'
# TODO: move `check-*` and `files-changed` jobs to the "Caller" Workflow
# We should care about that as Github has limitations:
# - You can connect up to four levels of workflows
# - You can call a maximum of 20 unique reusable workflows from a single workflow file.
# https://docs.github.com/en/actions/sharing-automations/reusing-workflows#limitations
permissions:
contents: read
jobs:
make-all:
if: |
inputs.pg_versions != '[]' || inputs.rebuild_rust_code || inputs.rebuild_everything ||
contains(github.event.pull_request.labels.*.name, 'run-extra-build-macos') ||
contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
github.ref_name == 'main'
timeout-minutes: 60
runs-on: macos-15
env:
# Use release build only, to have less debug info around
# Hence keeping target/ (and general cache size) smaller
BUILD_TYPE: release
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Checkout main repo
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
submodules: true
- uses: ./.github/actions/prepare-for-subzero
with:
token: ${{ secrets.CI_ACCESS_TOKEN }}
- name: Install build dependencies
run: |
brew install flex bison openssl protobuf icu4c
- name: Set extra env for macOS
run: |
echo 'LDFLAGS=-L/usr/local/opt/openssl@3/lib' >> $GITHUB_ENV
echo 'CPPFLAGS=-I/usr/local/opt/openssl@3/include' >> $GITHUB_ENV
- name: Restore "pg_install/" cache
id: cache_pg
uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
with:
path: pg_install
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-install-v14-${{ hashFiles('Makefile', 'postgres.mk', 'vendor/revisions.json') }}
- name: Checkout vendor/postgres submodules
if: steps.cache_pg.outputs.cache-hit != 'true'
run: |
git submodule init
git submodule update --depth 1 --recursive
- name: Build Postgres
if: steps.cache_pg.outputs.cache-hit != 'true'
run: |
make postgres -j$(sysctl -n hw.ncpu)
# This isn't strictly necessary, but it makes the cached and non-cached builds more similar,
# When pg_install is restored from cache, there is no 'build/' directory. By removing it
# in a non-cached build too, we enforce that the rest of the steps don't depend on it,
# so that we notice any build caching bugs earlier.
- name: Remove build artifacts
if: steps.cache_pg.outputs.cache-hit != 'true'
run: |
rm -rf build
# Explicitly update the rust toolchain before running 'make'. The parallel make build can
# invoke 'cargo build' more than once in parallel, for different crates. That's OK, 'cargo'
# does its own locking to prevent concurrent builds from stepping on each other's
# toes. However, it will first try to update the toolchain, and that step is not locked the
# same way. To avoid two toolchain updates running in parallel and stepping on each other's
# toes, ensure that the toolchain is up-to-date beforehand.
- name: Update rust toolchain
run: |
rustup --version &&
rustup update &&
rustup show
- name: Cache cargo deps
uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
with:
path: |
~/.cargo/registry
!~/.cargo/registry/src
~/.cargo/git
target
key: v1-${{ runner.os }}-${{ runner.arch }}-cargo-${{ hashFiles('./Cargo.lock') }}-${{ hashFiles('./rust-toolchain.toml') }}-rust
# Build the neon-specific postgres extensions, and all the Rust bits.
#
# Pass PG_INSTALL_CACHED=1 because PostgreSQL was already built and cached
# separately.
- name: Build all
run: PG_INSTALL_CACHED=1 BUILD_TYPE=release make -j$(sysctl -n hw.ncpu) all
- name: Check that no warnings are produced
run: ./run_clippy.sh

View File

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

File diff suppressed because it is too large Load Diff

View File

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

View File

@@ -1,145 +0,0 @@
name: Build and Test with Sanitizers
on:
schedule:
# * is a special character in YAML so you have to quote this string
# ┌───────────── minute (0 - 59)
# │ ┌───────────── hour (0 - 23)
# │ │ ┌───────────── day of the month (1 - 31)
# │ │ │ ┌───────────── month (1 - 12 or JAN-DEC)
# │ │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
- cron: '0 1 * * *' # run once a day, timezone is utc
workflow_dispatch:
defaults:
run:
shell: bash -euxo pipefail {0}
concurrency:
# Allow only one workflow per any non-`main` branch.
group: ${{ github.workflow }}-${{ github.ref_name }}-${{ github.ref_name == 'main' && github.sha || 'anysha' }}
cancel-in-progress: true
env:
RUST_BACKTRACE: 1
COPT: '-Werror'
jobs:
tag:
runs-on: [ self-hosted, small ]
container: ${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}.dkr.ecr.${{ vars.AWS_ECR_REGION }}.amazonaws.com/base:pinned
outputs:
build-tag: ${{steps.build-tag.outputs.tag}}
steps:
# Need `fetch-depth: 0` to count the number of commits in the branch
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
fetch-depth: 0
- name: Get build tag
run: |
echo run:$GITHUB_RUN_ID
echo ref:$GITHUB_REF_NAME
echo rev:$(git rev-list --count HEAD)
if [[ "$GITHUB_REF_NAME" == "main" ]]; then
echo "tag=$(git rev-list --count HEAD)" >> $GITHUB_OUTPUT
elif [[ "$GITHUB_REF_NAME" == "release" ]]; then
echo "tag=release-$(git rev-list --count HEAD)" >> $GITHUB_OUTPUT
elif [[ "$GITHUB_REF_NAME" == "release-proxy" ]]; then
echo "tag=release-proxy-$(git rev-list --count HEAD)" >> $GITHUB_OUTPUT
elif [[ "$GITHUB_REF_NAME" == "release-compute" ]]; then
echo "tag=release-compute-$(git rev-list --count HEAD)" >> $GITHUB_OUTPUT
else
echo "GITHUB_REF_NAME (value '$GITHUB_REF_NAME') is not set to either 'main' or 'release', 'release-proxy', 'release-compute'"
echo "tag=$GITHUB_RUN_ID" >> $GITHUB_OUTPUT
fi
shell: bash
id: build-tag
build-build-tools-image:
uses: ./.github/workflows/build-build-tools-image.yml
secrets: inherit
build-and-test-locally:
needs: [ tag, build-build-tools-image ]
strategy:
fail-fast: false
matrix:
arch: [ x64, arm64 ]
build-type: [ release ]
uses: ./.github/workflows/_build-and-test-locally.yml
with:
arch: ${{ matrix.arch }}
build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
build-tag: ${{ needs.tag.outputs.build-tag }}
build-type: ${{ matrix.build-type }}
rerun-failed: false
test-cfg: '[{"pg_version":"v17"}]'
sanitizers: enabled
secrets: inherit
create-test-report:
needs: [ build-and-test-locally, build-build-tools-image ]
if: ${{ !cancelled() }}
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: write
pull-requests: write
outputs:
report-url: ${{ steps.create-allure-report.outputs.report-url }}
runs-on: [ self-hosted, small ]
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
credentials:
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Create Allure report
if: ${{ !cancelled() }}
id: create-allure-report
uses: ./.github/actions/allure-report-generate
with:
store-test-results-into-db: true
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
- uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
if: ${{ !cancelled() }}
with:
# Retry script for 5XX server errors: https://github.com/actions/github-script#retries
retries: 5
script: |
const report = {
reportUrl: "${{ steps.create-allure-report.outputs.report-url }}",
reportJsonUrl: "${{ steps.create-allure-report.outputs.report-json-url }}",
}
const coverage = {}
const script = require("./scripts/comment-test-report.js")
await script({
github,
context,
fetch,
report,
coverage,
})

View File

@@ -1,69 +0,0 @@
name: cargo deny checks
on:
workflow_call:
inputs:
build-tools-image:
required: false
type: string
schedule:
- cron: '0 10 * * *'
permissions:
contents: read
jobs:
cargo-deny:
strategy:
matrix:
ref: >-
${{
fromJSON(
github.event_name == 'schedule'
&& '["main","release","release-proxy","release-compute"]'
|| format('["{0}"]', github.sha)
)
}}
runs-on: [self-hosted, small]
permissions:
packages: read
container:
image: ${{ inputs.build-tools-image || 'ghcr.io/neondatabase/build-tools:pinned' }}
credentials:
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Checkout
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
ref: ${{ matrix.ref }}
- name: Check rust licenses/bans/advisories/sources
env:
CARGO_DENY_TARGET: >-
${{ github.event_name == 'schedule' && 'advisories' || 'all' }}
run: cargo deny check --hide-inclusion-graph $CARGO_DENY_TARGET
- name: Post to a Slack channel
if: ${{ github.event_name == 'schedule' && failure() }}
uses: slackapi/slack-github-action@485a9d42d3a73031f12ec201c457e2162c45d02d # v2.0.0
with:
method: chat.postMessage
token: ${{ secrets.SLACK_BOT_TOKEN }}
payload: |
channel: ${{ vars.SLACK_ON_CALL_DEVPROD_STREAM }}
text: |
Periodic cargo-deny on ${{ matrix.ref }}: ${{ job.status }}
<${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}|GitHub Run>
Fixing the problem should be fairly straight forward from the logs. If not, <#${{ vars.SLACK_RUST_CHANNEL_ID }}> is there to help.
Pinging <!subteam^S0838JPSH32|@oncall-devprod>.

View File

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

View File

@@ -18,11 +18,6 @@ jobs:
check-permissions:
runs-on: ubuntu-22.04
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@0634a2670c59f64b4a01f0f96f84700a4088b9f0 # v2.12.0
with:
egress-policy: audit
- name: Disallow CI runs on PRs from forks
if: |
inputs.github-event-name == 'pull_request' &&

View File

@@ -11,11 +11,6 @@ jobs:
cleanup:
runs-on: ubuntu-22.04
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@0634a2670c59f64b4a01f0f96f84700a4088b9f0 # v2.12.0
with:
egress-policy: audit
- name: Cleanup
run: |
gh extension install actions/gh-actions-cache

View File

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

View File

@@ -1,138 +0,0 @@
name: Cloud Regression Test
on:
schedule:
# * is a special character in YAML so you have to quote this string
# ┌───────────── minute (0 - 59)
# │ ┌───────────── hour (0 - 23)
# │ │ ┌───────────── day of the month (1 - 31)
# │ │ │ ┌───────────── month (1 - 12 or JAN-DEC)
# │ │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
- cron: '45 1 * * *' # run once a day, timezone is utc
workflow_dispatch: # adds ability to run this manually
defaults:
run:
shell: bash -euxo pipefail {0}
concurrency:
# Allow only one workflow
group: ${{ github.workflow }}
cancel-in-progress: true
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: write
jobs:
regress:
env:
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
TEST_OUTPUT: /tmp/test_output
BUILD_TYPE: remote
strategy:
fail-fast: false
matrix:
pg-version: [16, 17]
runs-on: us-east-2
container:
image: ghcr.io/neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
submodules: true
- name: Patch the test
env:
PG_VERSION: ${{matrix.pg-version}}
run: |
cd "vendor/postgres-v${PG_VERSION}"
patch -p1 < "../../compute/patches/cloud_regress_pg${PG_VERSION}.patch"
- name: Generate a random password
id: pwgen
run: |
set +x
DBPASS=$(dd if=/dev/random bs=48 count=1 2>/dev/null | base64)
echo "::add-mask::${DBPASS//\//}"
echo DBPASS="${DBPASS//\//}" >> "${GITHUB_OUTPUT}"
- name: Change tests according to the generated password
env:
DBPASS: ${{ steps.pwgen.outputs.DBPASS }}
PG_VERSION: ${{matrix.pg-version}}
run: |
cd vendor/postgres-v"${PG_VERSION}"/src/test/regress
for fname in sql/*.sql expected/*.out; do
sed -i.bak s/NEON_PASSWORD_PLACEHOLDER/"'${DBPASS}'"/ "${fname}"
done
for ph in $(grep NEON_MD5_PLACEHOLDER expected/password.out | awk '{print $3;}' | sort | uniq); do
USER=$(echo "${ph}" | cut -c 22-)
MD5=md5$(echo -n "${DBPASS}${USER}" | md5sum | awk '{print $1;}')
sed -i.bak "s/${ph}/${MD5}/" expected/password.out
done
- name: Download Neon artifact
uses: ./.github/actions/download
with:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Create a new branch
id: create-branch
uses: ./.github/actions/neon-branch-create
with:
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
project_id: ${{ vars[format('PGREGRESS_PG{0}_PROJECT_ID', matrix.pg-version)] }}
- name: Run the regression tests
uses: ./.github/actions/run-python-test-set
with:
build_type: ${{ env.BUILD_TYPE }}
test_selection: cloud_regress
pg_version: ${{matrix.pg-version}}
extra_params: -m remote_cluster
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
BENCHMARK_CONNSTR: ${{steps.create-branch.outputs.dsn}}
- name: Delete branch
if: always()
uses: ./.github/actions/neon-branch-delete
with:
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
project_id: ${{ vars[format('PGREGRESS_PG{0}_PROJECT_ID', matrix.pg-version)] }}
branch_id: ${{steps.create-branch.outputs.branch_id}}
- name: Create Allure report
id: create-allure-report
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
with:
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@fcfb566f8b0aab22203f066d80ca1d7e4b5d05b3 # v1.27.1
with:
channel-id: ${{ vars.SLACK_ON_CALL_QA_STAGING_STREAM }}
slack-message: |
Periodic pg_regress on staging: ${{ job.status }}
<${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}|GitHub Run>
<${{ steps.create-allure-report.outputs.report-url }}|Allure report>
env:
SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}

View File

@@ -1,43 +0,0 @@
name: Fast forward merge
on:
pull_request:
types: [labeled]
branches:
- release
- release-proxy
- release-compute
jobs:
fast-forward:
if: ${{ github.event.label.name == 'fast-forward' }}
runs-on: ubuntu-22.04
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@0634a2670c59f64b4a01f0f96f84700a4088b9f0 # v2.12.0
with:
egress-policy: audit
- name: Remove fast-forward label to PR
env:
GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
run: |
gh pr edit ${{ github.event.pull_request.number }} --repo "${GITHUB_REPOSITORY}" --remove-label "fast-forward"
- name: Fast forwarding
uses: sequoia-pgp/fast-forward@ea7628bedcb0b0b96e94383ada458d812fca4979
# See https://docs.github.com/en/graphql/reference/enums#mergestatestatus
if: ${{ contains(fromJSON('["clean", "unstable"]'), github.event.pull_request.mergeable_state) }}
with:
merge: true
comment: on-error
github_token: ${{ secrets.CI_ACCESS_TOKEN }}
- name: Comment if mergeable_state is not clean
if: ${{ !contains(fromJSON('["clean", "unstable"]'), github.event.pull_request.mergeable_state) }}
env:
GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
run: |
gh pr comment ${{ github.event.pull_request.number }} \
--repo "${GITHUB_REPOSITORY}" \
--body "Not trying to forward pull-request, because \`mergeable_state\` is \`${{ github.event.pull_request.mergeable_state }}\`, not \`clean\` or \`unstable\`."

View File

@@ -1,82 +0,0 @@
name: Force Test Upgrading of Extension
on:
schedule:
# * is a special character in YAML so you have to quote this string
# ┌───────────── minute (0 - 59)
# │ ┌───────────── hour (0 - 23)
# │ │ ┌───────────── day of the month (1 - 31)
# │ │ │ ┌───────────── month (1 - 12 or JAN-DEC)
# │ │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
- cron: '45 2 * * *' # run once a day, timezone is utc
workflow_dispatch: # adds ability to run this manually
defaults:
run:
shell: bash -euxo pipefail {0}
concurrency:
# Allow only one workflow
group: ${{ github.workflow }}
cancel-in-progress: true
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: read
jobs:
regress:
strategy:
fail-fast: false
matrix:
pg-version: [16, 17]
runs-on: small
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
submodules: false
- name: Get the last compute release tag
id: get-last-compute-release-tag
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
tag=$(gh api -q '[.[].tag_name | select(startswith("release-compute"))][0]'\
-H "Accept: application/vnd.github+json" \
-H "X-GitHub-Api-Version: 2022-11-28" \
"/repos/${GITHUB_REPOSITORY}/releases")
echo tag=${tag} >> ${GITHUB_OUTPUT}
- name: Test extension upgrade
timeout-minutes: 60
env:
NEW_COMPUTE_TAG: latest
OLD_COMPUTE_TAG: ${{ steps.get-last-compute-release-tag.outputs.tag }}
TEST_EXTENSIONS_TAG: ${{ steps.get-last-compute-release-tag.outputs.tag }}
PG_VERSION: ${{ matrix.pg-version }}
FORCE_ALL_UPGRADE_TESTS: true
run: ./docker-compose/test_extensions_upgrade.sh
- name: Print logs and clean up
if: always()
run: |
docker compose --profile test-extensions -f ./docker-compose/docker-compose.yml logs || true
docker compose --profile test-extensions -f ./docker-compose/docker-compose.yml down
- name: Post to the Slack channel
if: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@fcfb566f8b0aab22203f066d80ca1d7e4b5d05b3 # v1.27.1
with:
channel-id: ${{ vars.SLACK_ON_CALL_QA_STAGING_STREAM }}
slack-message: |
Test upgrading of extensions: ${{ job.status }}
<${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}|GitHub Run>
env:
SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}

View File

@@ -1,200 +0,0 @@
name: benchmarking ingest
on:
# uncomment to run on push for debugging your PR
# push:
# branches: [ your branch ]
schedule:
# * is a special character in YAML so you have to quote this string
# ┌───────────── minute (0 - 59)
# │ ┌───────────── hour (0 - 23)
# │ │ ┌───────────── day of the month (1 - 31)
# │ │ │ ┌───────────── month (1 - 12 or JAN-DEC)
# │ │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
- cron: '0 9 * * *' # run once a day, timezone is utc
workflow_dispatch: # adds ability to run this manually
defaults:
run:
shell: bash -euxo pipefail {0}
concurrency:
# Allow only one workflow globally because we need dedicated resources which only exist once
group: ingest-bench-workflow
cancel-in-progress: true
permissions:
contents: read
jobs:
ingest:
strategy:
fail-fast: false # allow other variants to continue even if one fails
matrix:
include:
- target_project: new_empty_project_stripe_size_2048
stripe_size: 2048 # 16 MiB
postgres_version: 16
disable_sharding: false
- target_project: new_empty_project_stripe_size_32768
stripe_size: 32768 # 256 MiB # note that this is different from null because using null will shard_split the project only if it reaches the threshold
# while here it is sharded from the beginning with a shard size of 256 MiB
disable_sharding: false
postgres_version: 16
- target_project: new_empty_project
stripe_size: null # run with neon defaults which will shard split only when reaching the threshold
disable_sharding: false
postgres_version: 16
- target_project: new_empty_project
stripe_size: null # run with neon defaults which will shard split only when reaching the threshold
disable_sharding: false
postgres_version: 17
- target_project: large_existing_project
stripe_size: null # cannot re-shared or choose different stripe size for existing, already sharded project
disable_sharding: false
postgres_version: 16
- target_project: new_empty_project_unsharded
stripe_size: null # run with neon defaults which will shard split only when reaching the threshold
disable_sharding: true
postgres_version: 16
max-parallel: 1 # we want to run each stripe size sequentially to be able to compare the results
permissions:
contents: write
statuses: write
id-token: write # aws-actions/configure-aws-credentials
env:
PG_CONFIG: /tmp/neon/pg_install/v16/bin/pg_config
PSQL: /tmp/neon/pg_install/v16/bin/psql
PG_16_LIB_PATH: /tmp/neon/pg_install/v16/lib
PGCOPYDB: /pgcopydb/bin/pgcopydb
PGCOPYDB_LIB_PATH: /pgcopydb/lib
runs-on: [ self-hosted, us-east-2, x64 ]
container:
image: ghcr.io/neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
timeout-minutes: 1440
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Configure AWS credentials # necessary to download artefacts
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 18000 # 5 hours is currently max associated with IAM role
- name: Download Neon artifact
uses: ./.github/actions/download
with:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Create Neon Project
if: ${{ startsWith(matrix.target_project, 'new_empty_project') }}
id: create-neon-project-ingest-target
uses: ./.github/actions/neon-project-create
with:
region_id: aws-us-east-2
postgres_version: ${{ matrix.postgres_version }}
compute_units: '[7, 7]' # we want to test large compute here to avoid compute-side bottleneck
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
shard_split_project: ${{ matrix.stripe_size != null && 'true' || 'false' }}
admin_api_key: ${{ secrets.NEON_STAGING_ADMIN_API_KEY }}
shard_count: 8
stripe_size: ${{ matrix.stripe_size }}
disable_sharding: ${{ matrix.disable_sharding }}
- name: Initialize Neon project
if: ${{ startsWith(matrix.target_project, 'new_empty_project') }}
env:
BENCHMARK_INGEST_TARGET_CONNSTR: ${{ steps.create-neon-project-ingest-target.outputs.dsn }}
NEW_PROJECT_ID: ${{ steps.create-neon-project-ingest-target.outputs.project_id }}
run: |
echo "Initializing Neon project with project_id: ${NEW_PROJECT_ID}"
export LD_LIBRARY_PATH=${PG_16_LIB_PATH}
${PSQL} "${BENCHMARK_INGEST_TARGET_CONNSTR}" -c "CREATE EXTENSION IF NOT EXISTS neon; CREATE EXTENSION IF NOT EXISTS neon_utils;"
echo "BENCHMARK_INGEST_TARGET_CONNSTR=${BENCHMARK_INGEST_TARGET_CONNSTR}" >> $GITHUB_ENV
- name: Create Neon Branch for large tenant
if: ${{ matrix.target_project == 'large_existing_project' }}
id: create-neon-branch-ingest-target
uses: ./.github/actions/neon-branch-create
with:
project_id: ${{ vars.BENCHMARK_INGEST_TARGET_PROJECTID }}
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
- name: Initialize Neon project
if: ${{ matrix.target_project == 'large_existing_project' }}
env:
BENCHMARK_INGEST_TARGET_CONNSTR: ${{ steps.create-neon-branch-ingest-target.outputs.dsn }}
NEW_BRANCH_ID: ${{ steps.create-neon-branch-ingest-target.outputs.branch_id }}
run: |
echo "Initializing Neon branch with branch_id: ${NEW_BRANCH_ID}"
export LD_LIBRARY_PATH=${PG_16_LIB_PATH}
# Extract the part before the database name
base_connstr="${BENCHMARK_INGEST_TARGET_CONNSTR%/*}"
# Extract the query parameters (if any) after the database name
query_params="${BENCHMARK_INGEST_TARGET_CONNSTR#*\?}"
# Reconstruct the new connection string
if [ "$query_params" != "$BENCHMARK_INGEST_TARGET_CONNSTR" ]; then
new_connstr="${base_connstr}/neondb?${query_params}"
else
new_connstr="${base_connstr}/neondb"
fi
${PSQL} "${new_connstr}" -c "drop database ludicrous;"
${PSQL} "${new_connstr}" -c "CREATE DATABASE ludicrous;"
if [ "$query_params" != "$BENCHMARK_INGEST_TARGET_CONNSTR" ]; then
BENCHMARK_INGEST_TARGET_CONNSTR="${base_connstr}/ludicrous?${query_params}"
else
BENCHMARK_INGEST_TARGET_CONNSTR="${base_connstr}/ludicrous"
fi
${PSQL} "${BENCHMARK_INGEST_TARGET_CONNSTR}" -c "CREATE EXTENSION IF NOT EXISTS neon; CREATE EXTENSION IF NOT EXISTS neon_utils;"
echo "BENCHMARK_INGEST_TARGET_CONNSTR=${BENCHMARK_INGEST_TARGET_CONNSTR}" >> $GITHUB_ENV
- name: Invoke pgcopydb
uses: ./.github/actions/run-python-test-set
with:
build_type: remote
test_selection: performance/test_perf_ingest_using_pgcopydb.py
run_in_parallel: false
extra_params: -s -m remote_cluster --timeout 86400 -k test_ingest_performance_using_pgcopydb
pg_version: v${{ matrix.postgres_version }}
save_perf_report: true
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
BENCHMARK_INGEST_SOURCE_CONNSTR: ${{ secrets.BENCHMARK_INGEST_SOURCE_CONNSTR }}
TARGET_PROJECT_TYPE: ${{ matrix.target_project }}
# we report PLATFORM in zenbenchmark NeonBenchmarker perf database and want to distinguish between new project and large tenant
PLATFORM: "${{ matrix.target_project }}-us-east-2-staging"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
- name: show tables sizes after ingest
run: |
export LD_LIBRARY_PATH=${PG_16_LIB_PATH}
${PSQL} "${BENCHMARK_INGEST_TARGET_CONNSTR}" -c "\dt+"
- name: Delete Neon Project
if: ${{ always() && startsWith(matrix.target_project, 'new_empty_project') }}
uses: ./.github/actions/neon-project-delete
with:
project_id: ${{ steps.create-neon-project-ingest-target.outputs.project_id }}
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
- name: Delete Neon Branch for large tenant
if: ${{ always() && matrix.target_project == 'large_existing_project' }}
uses: ./.github/actions/neon-branch-delete
with:
project_id: ${{ vars.BENCHMARK_INGEST_TARGET_PROJECTID }}
branch_id: ${{ steps.create-neon-branch-ingest-target.outputs.branch_id }}
api_key: ${{ secrets.NEON_STAGING_API_KEY }}

View File

@@ -27,11 +27,6 @@ jobs:
is-member: ${{ steps.check-user.outputs.is-member }}
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@0634a2670c59f64b4a01f0f96f84700a4088b9f0 # v2.12.0
with:
egress-policy: audit
- name: Check whether `${{ github.actor }}` is a member of `${{ github.repository_owner }}`
id: check-user
env:
@@ -74,11 +69,6 @@ jobs:
issues: write # for `gh issue edit`
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@0634a2670c59f64b4a01f0f96f84700a4088b9f0 # v2.12.0
with:
egress-policy: audit
- name: Add `${{ env.LABEL }}` label
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}

View File

@@ -1,203 +0,0 @@
name: large oltp benchmark
on:
# uncomment to run on push for debugging your PR
#push:
# branches: [ bodobolero/synthetic_oltp_workload ]
schedule:
# * is a special character in YAML so you have to quote this string
# ┌───────────── minute (0 - 59)
# │ ┌───────────── hour (0 - 23)
# │ │ ┌───────────── day of the month (1 - 31)
# │ │ │ ┌───────────── month (1 - 12 or JAN-DEC)
# │ │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
- cron: '0 15 * * 0,2,4' # run on Sunday, Tuesday, Thursday at 3 PM UTC
workflow_dispatch: # adds ability to run this manually
defaults:
run:
shell: bash -euxo pipefail {0}
concurrency:
# Allow only one workflow globally because we need dedicated resources which only exist once
group: large-oltp-bench-workflow
cancel-in-progress: false
permissions:
contents: read
jobs:
oltp:
strategy:
fail-fast: false # allow other variants to continue even if one fails
matrix:
include:
# test only read-only custom scripts in new branch without database maintenance
- target: new_branch
custom_scripts: select_any_webhook_with_skew.sql@300 select_recent_webhook.sql@397 select_prefetch_webhook.sql@3
test_maintenance: false
# test all custom scripts in new branch with database maintenance
- target: new_branch
custom_scripts: insert_webhooks.sql@200 select_any_webhook_with_skew.sql@300 select_recent_webhook.sql@397 select_prefetch_webhook.sql@3 IUD_one_transaction.sql@100
test_maintenance: true
# test all custom scripts in reuse branch with database maintenance
- target: reuse_branch
custom_scripts: insert_webhooks.sql@200 select_any_webhook_with_skew.sql@300 select_recent_webhook.sql@397 select_prefetch_webhook.sql@3 IUD_one_transaction.sql@100
test_maintenance: true
max-parallel: 1 # we want to run each benchmark sequentially to not have noisy neighbors on shared storage (PS, SK)
permissions:
contents: write
statuses: write
id-token: write # aws-actions/configure-aws-credentials
env:
TEST_PG_BENCH_DURATIONS_MATRIX: "1h" # todo update to > 1 h
TEST_PGBENCH_CUSTOM_SCRIPTS: ${{ matrix.custom_scripts }}
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
PG_VERSION: 16 # pre-determined by pre-determined project
TEST_OUTPUT: /tmp/test_output
BUILD_TYPE: remote
PLATFORM: ${{ matrix.target }}
runs-on: [ self-hosted, us-east-2, x64 ]
container:
image: ghcr.io/neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
# Increase timeout to 2 days, default timeout is 6h - database maintenance can take a long time
# (normally 1h pgbench, 3h vacuum analyze 3.5h re-index) x 2 = 15h, leave some buffer for regressions
# in one run vacuum didn't finish within 12 hours
timeout-minutes: 2880
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Configure AWS credentials # necessary to download artefacts
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 18000 # 5 hours is currently max associated with IAM role
- name: Download Neon artifact
uses: ./.github/actions/download
with:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Create Neon Branch for large tenant
if: ${{ matrix.target == 'new_branch' }}
id: create-neon-branch-oltp-target
uses: ./.github/actions/neon-branch-create
with:
project_id: ${{ vars.BENCHMARK_LARGE_OLTP_PROJECTID }}
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
- name: Set up Connection String
id: set-up-connstr
run: |
case "${{ matrix.target }}" in
new_branch)
CONNSTR=${{ steps.create-neon-branch-oltp-target.outputs.dsn }}
;;
reuse_branch)
CONNSTR=${{ secrets.BENCHMARK_LARGE_OLTP_REUSE_CONNSTR }}
;;
*)
echo >&2 "Unknown target=${{ matrix.target }}"
exit 1
;;
esac
CONNSTR_WITHOUT_POOLER="${CONNSTR//-pooler/}"
echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
echo "connstr_without_pooler=${CONNSTR_WITHOUT_POOLER}" >> $GITHUB_OUTPUT
- name: Delete rows from prior runs in reuse branch
if: ${{ matrix.target == 'reuse_branch' }}
env:
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr_without_pooler }}
PG_CONFIG: /tmp/neon/pg_install/v16/bin/pg_config
PSQL: /tmp/neon/pg_install/v16/bin/psql
PG_16_LIB_PATH: /tmp/neon/pg_install/v16/lib
run: |
echo "$(date '+%Y-%m-%d %H:%M:%S') - Deleting rows in table webhook.incoming_webhooks from prior runs"
export LD_LIBRARY_PATH=${PG_16_LIB_PATH}
${PSQL} "${BENCHMARK_CONNSTR}" -c "SET statement_timeout = 0; DELETE FROM webhook.incoming_webhooks WHERE created_at > '2025-02-27 23:59:59+00';"
echo "$(date '+%Y-%m-%d %H:%M:%S') - Finished deleting rows in table webhook.incoming_webhooks from prior runs"
- name: Benchmark pgbench with custom-scripts
uses: ./.github/actions/run-python-test-set
with:
build_type: ${{ env.BUILD_TYPE }}
test_selection: performance
run_in_parallel: false
save_perf_report: true
extra_params: -m remote_cluster --timeout 7200 -k test_perf_oltp_large_tenant_pgbench
pg_version: ${{ env.PG_VERSION }}
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
- name: Benchmark database maintenance
if: ${{ matrix.test_maintenance }}
uses: ./.github/actions/run-python-test-set
with:
build_type: ${{ env.BUILD_TYPE }}
test_selection: performance
run_in_parallel: false
save_perf_report: true
extra_params: -m remote_cluster --timeout 172800 -k test_perf_oltp_large_tenant_maintenance
pg_version: ${{ env.PG_VERSION }}
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr_without_pooler }}
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
- name: Delete Neon Branch for large tenant
if: ${{ always() && matrix.target == 'new_branch' }}
uses: ./.github/actions/neon-branch-delete
with:
project_id: ${{ vars.BENCHMARK_LARGE_OLTP_PROJECTID }}
branch_id: ${{ steps.create-neon-branch-oltp-target.outputs.branch_id }}
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
- name: Configure AWS credentials # again because prior steps could have exceeded 5 hours
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 18000 # 5 hours
- name: Create Allure report
id: create-allure-report
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
with:
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@fcfb566f8b0aab22203f066d80ca1d7e4b5d05b3 # v1.27.1
with:
channel-id: "C06KHQVQ7U3" # on-call-qa-staging-stream
slack-message: |
Periodic large oltp perf testing: ${{ job.status }}
<${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}|GitHub Run>
<${{ steps.create-allure-report.outputs.report-url }}|Allure report>
env:
SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}

View File

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

View File

@@ -1,32 +0,0 @@
name: Lint Release PR
on:
pull_request:
branches:
- release
- release-proxy
- release-compute
permissions:
contents: read
jobs:
lint-release-pr:
runs-on: ubuntu-22.04
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Checkout PR branch
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
fetch-depth: 0 # Fetch full history for git operations
ref: ${{ github.event.pull_request.head.ref }}
- name: Run lint script
env:
RELEASE_BRANCH: ${{ github.base_ref }}
run: |
./.github/scripts/lint-release-pr.sh

View File

@@ -26,76 +26,139 @@ jobs:
with:
github-event-name: ${{ github.event_name}}
build-build-tools-image:
check-build-tools-image:
needs: [ check-permissions ]
uses: ./.github/workflows/check-build-tools-image.yml
build-build-tools-image:
needs: [ check-build-tools-image ]
uses: ./.github/workflows/build-build-tools-image.yml
with:
image-tag: ${{ needs.check-build-tools-image.outputs.image-tag }}
secrets: inherit
files-changed:
name: Detect what files changed
runs-on: ubuntu-22.04
timeout-minutes: 3
outputs:
v17: ${{ steps.files_changed.outputs.v17 }}
postgres_changes: ${{ steps.postgres_changes.outputs.changes }}
rebuild_rust_code: ${{ steps.files_changed.outputs.rust_code }}
rebuild_everything: ${{ steps.files_changed.outputs.rebuild_neon_extra || steps.files_changed.outputs.rebuild_macos }}
check-macos-build:
needs: [ check-permissions ]
if: |
contains(github.event.pull_request.labels.*.name, 'run-extra-build-macos') ||
contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
github.ref_name == 'main'
timeout-minutes: 90
runs-on: macos-14
env:
# Use release build only, to have less debug info around
# Hence keeping target/ (and general cache size) smaller
BUILD_TYPE: release
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Checkout
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
uses: actions/checkout@v4
with:
submodules: true
- name: Check for Postgres changes
uses: dorny/paths-filter@1441771bbfdd59dcd748680ee64ebd8faab1a242 #v3
id: files_changed
- name: Install macOS postgres dependencies
run: brew install flex bison openssl protobuf icu4c pkg-config
- name: Set pg 14 revision for caching
id: pg_v14_rev
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v14) >> $GITHUB_OUTPUT
- name: Set pg 15 revision for caching
id: pg_v15_rev
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v15) >> $GITHUB_OUTPUT
- name: Set pg 16 revision for caching
id: pg_v16_rev
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v16) >> $GITHUB_OUTPUT
- name: Set pg 17 revision for caching
id: pg_v17_rev
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v17) >> $GITHUB_OUTPUT
- name: Cache postgres v14 build
id: cache_pg_14
uses: actions/cache@v4
with:
token: ${{ github.token }}
filters: .github/file-filters.yaml
base: ${{ github.event_name != 'pull_request' && (github.event.merge_group.base_ref || github.ref_name) || '' }}
ref: ${{ github.event_name != 'pull_request' && (github.event.merge_group.head_ref || github.ref) || '' }}
path: pg_install/v14
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-${{ steps.pg_v14_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Filter out only v-string for build matrix
id: postgres_changes
env:
CHANGES: ${{ steps.files_changed.outputs.changes }}
- name: Cache postgres v15 build
id: cache_pg_15
uses: actions/cache@v4
with:
path: pg_install/v15
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-${{ steps.pg_v15_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Cache postgres v16 build
id: cache_pg_16
uses: actions/cache@v4
with:
path: pg_install/v16
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-${{ steps.pg_v16_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Cache postgres v17 build
id: cache_pg_17
uses: actions/cache@v4
with:
path: pg_install/v17
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-${{ steps.pg_v17_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Set extra env for macOS
run: |
v_strings_only_as_json_array=$(echo ${CHANGES} | jq '.[]|select(test("v\\d+"))' | jq --slurp -c)
echo "changes=${v_strings_only_as_json_array}" | tee -a "${GITHUB_OUTPUT}"
echo 'LDFLAGS=-L/usr/local/opt/openssl@3/lib' >> $GITHUB_ENV
echo 'CPPFLAGS=-I/usr/local/opt/openssl@3/include' >> $GITHUB_ENV
check-macos-build:
needs: [ check-permissions, files-changed ]
uses: ./.github/workflows/build-macos.yml
secrets: inherit
with:
pg_versions: ${{ needs.files-changed.outputs.postgres_changes }}
rebuild_rust_code: ${{ fromJSON(needs.files-changed.outputs.rebuild_rust_code) }}
rebuild_everything: ${{ fromJSON(needs.files-changed.outputs.rebuild_everything) }}
- name: Cache cargo deps
uses: actions/cache@v4
with:
path: |
~/.cargo/registry
!~/.cargo/registry/src
~/.cargo/git
target
key: v1-${{ runner.os }}-${{ runner.arch }}-cargo-${{ hashFiles('./Cargo.lock') }}-${{ hashFiles('./rust-toolchain.toml') }}-rust
- name: Build postgres v14
if: steps.cache_pg_14.outputs.cache-hit != 'true'
run: make postgres-v14 -j$(sysctl -n hw.ncpu)
- name: Build postgres v15
if: steps.cache_pg_15.outputs.cache-hit != 'true'
run: make postgres-v15 -j$(sysctl -n hw.ncpu)
- name: Build postgres v16
if: steps.cache_pg_16.outputs.cache-hit != 'true'
run: make postgres-v16 -j$(sysctl -n hw.ncpu)
- name: Build postgres v17
if: steps.cache_pg_17.outputs.cache-hit != 'true'
run: make postgres-v17 -j$(sysctl -n hw.ncpu)
- name: Build neon extensions
run: make neon-pg-ext -j$(sysctl -n hw.ncpu)
- name: Build walproposer-lib
run: make walproposer-lib -j$(sysctl -n hw.ncpu)
- name: Run cargo build
run: PQ_LIB_DIR=$(pwd)/pg_install/v16/lib cargo build --all --release
- name: Check that no warnings are produced
run: ./run_clippy.sh
gather-rust-build-stats:
needs: [ check-permissions, build-build-tools-image, files-changed ]
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: write
needs: [ check-permissions, build-build-tools-image ]
if: |
(needs.files-changed.outputs.v17 == 'true' || needs.files-changed.outputs.rebuild_everything == 'true') && (
contains(github.event.pull_request.labels.*.name, 'run-extra-build-stats') ||
contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
github.ref_name == 'main'
)
contains(github.event.pull_request.labels.*.name, 'run-extra-build-stats') ||
contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
github.ref_name == 'main'
runs-on: [ self-hosted, large ]
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
image: ${{ needs.build-build-tools-image.outputs.image }}
credentials:
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
options: --init
env:
@@ -105,13 +168,8 @@ jobs:
CARGO_INCREMENTAL: 0
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Checkout
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
uses: actions/checkout@v4
with:
submodules: true
@@ -123,33 +181,26 @@ jobs:
run: make walproposer-lib -j$(nproc)
- name: Produce the build stats
run: cargo build --all --release --timings -j$(nproc)
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 3600
run: PQ_LIB_DIR=$(pwd)/pg_install/v17/lib cargo build --all --release --timings -j$(nproc)
- name: Upload the build stats
id: upload-stats
env:
BUCKET: neon-github-public-dev
SHA: ${{ github.event.pull_request.head.sha || github.sha }}
AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
run: |
REPORT_URL=https://${BUCKET}.s3.amazonaws.com/build-stats/${SHA}/${GITHUB_RUN_ID}/cargo-timing.html
aws s3 cp --only-show-errors ./target/cargo-timings/cargo-timing.html "s3://${BUCKET}/build-stats/${SHA}/${GITHUB_RUN_ID}/"
echo "report-url=${REPORT_URL}" >> $GITHUB_OUTPUT
- name: Publish build stats report
uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
uses: actions/github-script@v7
env:
REPORT_URL: ${{ steps.upload-stats.outputs.report-url }}
SHA: ${{ github.event.pull_request.head.sha || github.sha }}
with:
# Retry script for 5XX server errors: https://github.com/actions/github-script#retries
retries: 5
script: |
const { REPORT_URL, SHA } = process.env

View File

@@ -1,14 +1,14 @@
name: Periodic pagebench performance test on unit-perf-aws-arm runners
name: Periodic pagebench performance test on dedicated EC2 machine in eu-central-1 region
on:
schedule:
# * is a special character in YAML so you have to quote this string
# ┌───────────── minute (0 - 59)
# ┌───────────── hour (0 - 23)
# │ ┌───────────── day of the month (1 - 31)
# │ │ ┌───────────── month (1 - 12 or JAN-DEC)
# │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
- cron: '0 */4 * * *' # Runs every 4 hours
# ┌───────────── minute (0 - 59)
# ┌───────────── hour (0 - 23)
# │ ┌───────────── day of the month (1 - 31)
# │ │ ┌───────────── month (1 - 12 or JAN-DEC)
# │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
- cron: '0 18 * * *' # Runs at 6 PM UTC every day
workflow_dispatch: # Allows manual triggering of the workflow
inputs:
commit_hash:
@@ -16,11 +16,6 @@ on:
description: 'The long neon repo commit hash for the system under test (pageserver) to be tested.'
required: false
default: ''
recreate_snapshots:
type: boolean
description: 'Recreate snapshots - !!!WARNING!!! We should only recreate snapshots if the previous ones are no longer compatible. Otherwise benchmarking results are not comparable across runs.'
required: false
default: false
defaults:
run:
@@ -30,252 +25,131 @@ concurrency:
group: ${{ github.workflow }}
cancel-in-progress: false
permissions:
contents: read
jobs:
run_periodic_pagebench_test:
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: write
pull-requests: write
runs-on: [ self-hosted, unit-perf-aws-arm ]
trigger_bench_on_ec2_machine_in_eu_central_1:
runs-on: [ self-hosted, small ]
container:
image: ghcr.io/neondatabase/build-tools:pinned-bookworm
image: neondatabase/build-tools:pinned
credentials:
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
options: --init
timeout-minutes: 360 # Set the timeout to 6 hours
env:
API_KEY: ${{ secrets.PERIODIC_PAGEBENCH_EC2_RUNNER_API_KEY }}
RUN_ID: ${{ github.run_id }}
DEFAULT_PG_VERSION: 16
BUILD_TYPE: release
RUST_BACKTRACE: 1
# NEON_ENV_BUILDER_USE_OVERLAYFS_FOR_SNAPSHOTS: 1 - doesn't work without root in container
S3_BUCKET: neon-github-public-dev
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
AWS_ACCESS_KEY_ID: ${{ secrets.AWS_EC2_US_TEST_RUNNER_ACCESS_KEY_ID }}
AWS_SECRET_ACCESS_KEY : ${{ secrets.AWS_EC2_US_TEST_RUNNER_ACCESS_KEY_SECRET }}
AWS_DEFAULT_REGION : "eu-central-1"
AWS_INSTANCE_ID : "i-02a59a3bf86bc7e74"
steps:
# we don't need the neon source code because we run everything remotely
# however we still need the local github actions to run the allure step below
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@v4
- name: Set up the environment which depends on $RUNNER_TEMP on nvme drive
id: set-env
shell: bash -euxo pipefail {0}
- name: Show my own (github runner) external IP address - usefull for IP allowlisting
run: curl https://ifconfig.me
- name: Start EC2 instance and wait for the instance to boot up
run: |
{
echo "NEON_DIR=${RUNNER_TEMP}/neon"
echo "NEON_BIN=${RUNNER_TEMP}/neon/bin"
echo "POSTGRES_DISTRIB_DIR=${RUNNER_TEMP}/neon/pg_install"
echo "LD_LIBRARY_PATH=${RUNNER_TEMP}/neon/pg_install/v${DEFAULT_PG_VERSION}/lib"
echo "BACKUP_DIR=${RUNNER_TEMP}/instance_store/saved_snapshots"
echo "TEST_OUTPUT=${RUNNER_TEMP}/neon/test_output"
echo "PERF_REPORT_DIR=${RUNNER_TEMP}/neon/test_output/perf-report-local"
echo "ALLURE_DIR=${RUNNER_TEMP}/neon/test_output/allure-results"
echo "ALLURE_RESULTS_DIR=${RUNNER_TEMP}/neon/test_output/allure-results/results"
} >> "$GITHUB_ENV"
aws ec2 start-instances --instance-ids $AWS_INSTANCE_ID
aws ec2 wait instance-running --instance-ids $AWS_INSTANCE_ID
sleep 60 # sleep some time to allow cloudinit and our API server to start up
echo "allure_results_dir=${RUNNER_TEMP}/neon/test_output/allure-results/results" >> "$GITHUB_OUTPUT"
- name: Determine public IP of the EC2 instance and set env variable EC2_MACHINE_URL_US
run: |
public_ip=$(aws ec2 describe-instances --instance-ids $AWS_INSTANCE_ID --query 'Reservations[*].Instances[*].PublicIpAddress' --output text)
echo "Public IP of the EC2 instance: $public_ip"
echo "EC2_MACHINE_URL_US=https://${public_ip}:8443" >> $GITHUB_ENV
- uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 18000 # max 5 hours (needed in case commit hash is still being built)
- name: Determine commit hash
id: commit_hash
shell: bash -euxo pipefail {0}
env:
INPUT_COMMIT_HASH: ${{ github.event.inputs.commit_hash }}
run: |
if [[ -z "${INPUT_COMMIT_HASH}" ]]; then
COMMIT_HASH=$(curl -s https://api.github.com/repos/neondatabase/neon/commits/main | jq -r '.sha')
echo "COMMIT_HASH=$COMMIT_HASH" >> $GITHUB_ENV
echo "commit_hash=$COMMIT_HASH" >> "$GITHUB_OUTPUT"
echo "COMMIT_HASH_TYPE=latest" >> $GITHUB_ENV
if [ -z "$INPUT_COMMIT_HASH" ]; then
echo "COMMIT_HASH=$(curl -s https://api.github.com/repos/neondatabase/neon/commits/main | jq -r '.sha')" >> $GITHUB_ENV
else
COMMIT_HASH="${INPUT_COMMIT_HASH}"
echo "COMMIT_HASH=$COMMIT_HASH" >> $GITHUB_ENV
echo "commit_hash=$COMMIT_HASH" >> "$GITHUB_OUTPUT"
echo "COMMIT_HASH_TYPE=manual" >> $GITHUB_ENV
echo "COMMIT_HASH=$INPUT_COMMIT_HASH" >> $GITHUB_ENV
fi
- name: Checkout the neon repository at given commit hash
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
ref: ${{ steps.commit_hash.outputs.commit_hash }}
# does not reuse ./.github/actions/download because we need to download the artifact for the given commit hash
# example artifact
# s3://neon-github-public-dev/artifacts/48b870bc078bd2c450eb7b468e743b9c118549bf/15036827400/1/neon-Linux-X64-release-artifact.tar.zst /instance_store/artifacts/neon-Linux-release-artifact.tar.zst
- name: Determine artifact S3_KEY for given commit hash and download and extract artifact
id: artifact_prefix
shell: bash -euxo pipefail {0}
env:
ARCHIVE: ${{ runner.temp }}/downloads/neon-${{ runner.os }}-${{ runner.arch }}-release-artifact.tar.zst
COMMIT_HASH: ${{ env.COMMIT_HASH }}
COMMIT_HASH_TYPE: ${{ env.COMMIT_HASH_TYPE }}
- name: Start Bench with run_id
run: |
attempt=0
max_attempts=24 # 5 minutes * 24 = 2 hours
curl -k -X 'POST' \
"${EC2_MACHINE_URL_US}/start_test/${GITHUB_RUN_ID}" \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-H "Authorization: Bearer $API_KEY" \
-d "{\"neonRepoCommitHash\": \"${COMMIT_HASH}\"}"
while [[ $attempt -lt $max_attempts ]]; do
# the following command will fail until the artifacts are available ...
S3_KEY=$(aws s3api list-objects-v2 --bucket "$S3_BUCKET" --prefix "artifacts/$COMMIT_HASH/" \
| jq -r '.Contents[]?.Key' \
| grep "neon-${{ runner.os }}-${{ runner.arch }}-release-artifact.tar.zst" \
| sort --version-sort \
| tail -1) || true # ... thus ignore errors from the command
if [[ -n "${S3_KEY}" ]]; then
echo "Artifact found: $S3_KEY"
echo "S3_KEY=$S3_KEY" >> $GITHUB_ENV
- name: Poll Test Status
id: poll_step
run: |
status=""
while [[ "$status" != "failure" && "$status" != "success" ]]; do
response=$(curl -k -X 'GET' \
"${EC2_MACHINE_URL_US}/test_status/${GITHUB_RUN_ID}" \
-H 'accept: application/json' \
-H "Authorization: Bearer $API_KEY")
echo "Response: $response"
set +x
status=$(echo $response | jq -r '.status')
echo "Test status: $status"
if [[ "$status" == "failure" ]]; then
echo "Test failed"
exit 1 # Fail the job step if status is failure
elif [[ "$status" == "success" || "$status" == "null" ]]; then
break
elif [[ "$status" == "too_many_runs" ]]; then
echo "Too many runs already running"
echo "too_many_runs=true" >> "$GITHUB_OUTPUT"
exit 1
fi
# Increment attempt counter and sleep for 5 minutes
attempt=$((attempt + 1))
echo "Attempt $attempt of $max_attempts to find artifacts in S3 bucket s3://$S3_BUCKET/artifacts/$COMMIT_HASH failed. Retrying in 5 minutes..."
sleep 300 # Sleep for 5 minutes
sleep 60 # Poll every 60 seconds
done
if [[ -z "${S3_KEY}" ]]; then
echo "Error: artifact not found in S3 bucket s3://$S3_BUCKET/artifacts/$COMMIT_HASH" after 2 hours
else
mkdir -p $(dirname $ARCHIVE)
time aws s3 cp --only-show-errors s3://$S3_BUCKET/${S3_KEY} ${ARCHIVE}
mkdir -p ${NEON_DIR}
time tar -xf ${ARCHIVE} -C ${NEON_DIR}
rm -f ${ARCHIVE}
fi
- name: Download snapshots from S3
if: ${{ github.event_name != 'workflow_dispatch' || github.event.inputs.recreate_snapshots == 'false' || github.event.inputs.recreate_snapshots == '' }}
id: download_snapshots
shell: bash -euxo pipefail {0}
- name: Retrieve Test Logs
if: always() && steps.poll_step.outputs.too_many_runs != 'true'
run: |
# Download the snapshots from S3
mkdir -p ${TEST_OUTPUT}
mkdir -p $BACKUP_DIR
cd $BACKUP_DIR
mkdir parts
cd parts
PART=$(aws s3api list-objects-v2 --bucket $S3_BUCKET --prefix performance/pagebench/ \
| jq -r '.Contents[]?.Key' \
| grep -E 'shared-snapshots-[0-9]{4}-[0-9]{2}-[0-9]{2}' \
| sort \
| tail -1)
echo "Latest PART: $PART"
if [[ -z "$PART" ]]; then
echo "ERROR: No matching S3 key found" >&2
exit 1
fi
S3_KEY=$(dirname $PART)
time aws s3 cp --only-show-errors --recursive s3://${S3_BUCKET}/$S3_KEY/ .
cd $TEST_OUTPUT
time cat $BACKUP_DIR/parts/* | zstdcat | tar --extract --preserve-permissions
rm -rf ${BACKUP_DIR}
- name: Cache poetry deps
uses: actions/cache@v4
with:
path: ~/.cache/pypoetry/virtualenvs
key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-bookworm-${{ hashFiles('poetry.lock') }}
- name: Install Python deps
shell: bash -euxo pipefail {0}
run: ./scripts/pysync
# we need high number of open files for pagebench
- name: show ulimits
shell: bash -euxo pipefail {0}
curl -k -X 'GET' \
"${EC2_MACHINE_URL_US}/test_log/${GITHUB_RUN_ID}" \
-H 'accept: application/gzip' \
-H "Authorization: Bearer $API_KEY" \
--output "test_log_${GITHUB_RUN_ID}.gz"
- name: Unzip Test Log and Print it into this job's log
if: always() && steps.poll_step.outputs.too_many_runs != 'true'
run: |
ulimit -a
- name: Run pagebench testcase
shell: bash -euxo pipefail {0}
env:
CI: false # need to override this env variable set by github to enforce using snapshots
run: |
export PLATFORM=hetzner-unit-perf-${COMMIT_HASH_TYPE}
# report the commit hash of the neon repository in the revision of the test results
export GITHUB_SHA=${COMMIT_HASH}
rm -rf ${PERF_REPORT_DIR}
rm -rf ${ALLURE_RESULTS_DIR}
mkdir -p ${PERF_REPORT_DIR}
mkdir -p ${ALLURE_RESULTS_DIR}
PARAMS="--alluredir=${ALLURE_RESULTS_DIR} --tb=short --verbose -rA"
EXTRA_PARAMS="--out-dir ${PERF_REPORT_DIR} --durations-path $TEST_OUTPUT/benchmark_durations.json"
# run only two selected tests
# environment set by parent:
# RUST_BACKTRACE=1 DEFAULT_PG_VERSION=16 BUILD_TYPE=release
./scripts/pytest ${PARAMS} test_runner/performance/pageserver/pagebench/test_pageserver_max_throughput_getpage_at_latest_lsn.py::test_pageserver_characterize_throughput_with_n_tenants ${EXTRA_PARAMS}
./scripts/pytest ${PARAMS} test_runner/performance/pageserver/pagebench/test_pageserver_max_throughput_getpage_at_latest_lsn.py::test_pageserver_characterize_latencies_with_1_client_and_throughput_with_many_clients_one_tenant ${EXTRA_PARAMS}
- name: upload the performance metrics to the Neon performance database which is used by grafana dashboards to display the results
shell: bash -euxo pipefail {0}
run: |
export REPORT_FROM="$PERF_REPORT_DIR"
export GITHUB_SHA=${COMMIT_HASH}
time ./scripts/generate_and_push_perf_report.sh
- name: Upload test results
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-store
with:
report-dir: ${{ steps.set-env.outputs.allure_results_dir }}
unique-key: ${{ env.BUILD_TYPE }}-${{ env.DEFAULT_PG_VERSION }}-${{ runner.arch }}
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
gzip -d "test_log_${GITHUB_RUN_ID}.gz"
cat "test_log_${GITHUB_RUN_ID}"
- name: Create Allure report
id: create-allure-report
env:
AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
with:
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Upload snapshots
if: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.recreate_snapshots != 'false' && github.event.inputs.recreate_snapshots != '' }}
id: upload_snapshots
shell: bash -euxo pipefail {0}
run: |
mkdir -p $BACKUP_DIR
cd $TEST_OUTPUT
tar --create --preserve-permissions --file - shared-snapshots | zstd -o $BACKUP_DIR/shared_snapshots.tar.zst
cd $BACKUP_DIR
mkdir parts
split -b 1G shared_snapshots.tar.zst ./parts/shared_snapshots.tar.zst.part.
SNAPSHOT_DATE=$(date +%F) # YYYY-MM-DD
cd parts
time aws s3 cp --recursive . s3://${S3_BUCKET}/performance/pagebench/shared-snapshots-${SNAPSHOT_DATE}/
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@fcfb566f8b0aab22203f066d80ca1d7e4b5d05b3 # v1.27.1
uses: slackapi/slack-github-action@v1
with:
channel-id: "C06KHQVQ7U3" # on-call-qa-staging-stream
channel-id: "C033QLM5P7D" # dev-staging-stream
slack-message: "Periodic pagebench testing on dedicated hardware: ${{ job.status }}\n${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}"
env:
SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
- name: Cleanup Test Resources
if: always()
shell: bash -euxo pipefail {0}
env:
ARCHIVE: ${{ runner.temp }}/downloads/neon-${{ runner.os }}-${{ runner.arch }}-release-artifact.tar.zst
run: |
# Cleanup the test resources
if [[ -d "${BACKUP_DIR}" ]]; then
rm -rf ${BACKUP_DIR}
fi
if [[ -d "${TEST_OUTPUT}" ]]; then
rm -rf ${TEST_OUTPUT}
fi
if [[ -d "${NEON_DIR}" ]]; then
rm -rf ${NEON_DIR}
fi
rm -rf $(dirname $ARCHIVE)
- name: Cleanup Test Resources
if: always()
run: |
curl -k -X 'POST' \
"${EC2_MACHINE_URL_US}/cleanup_test/${GITHUB_RUN_ID}" \
-H 'accept: application/json' \
-H "Authorization: Bearer $API_KEY" \
-d ''
- name: Stop EC2 instance and wait for the instance to be stopped
if: always() && steps.poll_step.outputs.too_many_runs != 'true'
run: |
aws ec2 stop-instances --instance-ids $AWS_INSTANCE_ID
aws ec2 wait instance-stopped --instance-ids $AWS_INSTANCE_ID

View File

@@ -12,8 +12,8 @@ on:
pull_request:
paths:
- '.github/workflows/pg-clients.yml'
- 'test_runner/pg_clients/**/*.py'
- 'test_runner/logical_repl/**/*.py'
- 'test_runner/pg_clients/**'
- 'test_runner/logical_repl/**'
- 'poetry.lock'
workflow_dispatch:
@@ -25,13 +25,11 @@ defaults:
run:
shell: bash -euxo pipefail {0}
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write # require for posting a status update
env:
DEFAULT_PG_VERSION: 17
DEFAULT_PG_VERSION: 16
PLATFORM: neon-captest-new
AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
AWS_DEFAULT_REGION: eu-central-1
jobs:
@@ -41,11 +39,15 @@ jobs:
with:
github-event-name: ${{ github.event_name }}
build-build-tools-image:
permissions:
packages: write
check-build-tools-image:
needs: [ check-permissions ]
uses: ./.github/workflows/check-build-tools-image.yml
build-build-tools-image:
needs: [ check-build-tools-image ]
uses: ./.github/workflows/build-build-tools-image.yml
with:
image-tag: ${{ needs.check-build-tools-image.outputs.image-tag }}
secrets: inherit
test-logical-replication:
@@ -53,10 +55,10 @@ jobs:
runs-on: ubuntu-22.04
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
image: ${{ needs.build-build-tools-image.outputs.image }}
credentials:
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
options: --init --user root
services:
clickhouse:
@@ -90,12 +92,7 @@ jobs:
ports:
- 8083:8083
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- uses: actions/checkout@v4
- name: Download Neon artifact
uses: ./.github/actions/download
@@ -103,7 +100,6 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Create Neon Project
id: create-neon-project
@@ -111,8 +107,6 @@ jobs:
with:
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
postgres_version: ${{ env.DEFAULT_PG_VERSION }}
project_settings: >-
{"enable_logical_replication": true}
- name: Run tests
uses: ./.github/actions/run-python-test-set
@@ -122,7 +116,6 @@ jobs:
run_in_parallel: false
extra_params: -m remote_cluster
pg_version: ${{ env.DEFAULT_PG_VERSION }}
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
BENCHMARK_CONNSTR: ${{ steps.create-neon-project.outputs.dsn }}
@@ -139,13 +132,12 @@ jobs:
uses: ./.github/actions/allure-report-generate
with:
store-test-results-into-db: true
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
- name: Post to a Slack channel
if: github.event.schedule && failure()
uses: slackapi/slack-github-action@fcfb566f8b0aab22203f066d80ca1d7e4b5d05b3 # v1.27.1
uses: slackapi/slack-github-action@v1
with:
channel-id: "C06KHQVQ7U3" # on-call-qa-staging-stream
slack-message: |
@@ -158,19 +150,14 @@ jobs:
runs-on: ubuntu-22.04
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
image: ${{ needs.build-build-tools-image.outputs.image }}
credentials:
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
options: --init --user root
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- uses: actions/checkout@v4
- name: Download Neon artifact
uses: ./.github/actions/download
@@ -178,7 +165,6 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Create Neon Project
id: create-neon-project
@@ -195,7 +181,6 @@ jobs:
run_in_parallel: false
extra_params: -m remote_cluster
pg_version: ${{ env.DEFAULT_PG_VERSION }}
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
BENCHMARK_CONNSTR: ${{ steps.create-neon-project.outputs.dsn }}
@@ -212,13 +197,12 @@ jobs:
uses: ./.github/actions/allure-report-generate
with:
store-test-results-into-db: true
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
- name: Post to a Slack channel
if: github.event.schedule && failure()
uses: slackapi/slack-github-action@fcfb566f8b0aab22203f066d80ca1d7e4b5d05b3 # v1.27.1
uses: slackapi/slack-github-action@v1
with:
channel-id: "C06KHQVQ7U3" # on-call-qa-staging-stream
slack-message: |

View File

@@ -33,6 +33,10 @@ concurrency:
# No permission for GITHUB_TOKEN by default; the **minimal required** set of permissions should be granted in each job.
permissions: {}
env:
FROM_TAG: ${{ inputs.from-tag }}
TO_TAG: pinned
jobs:
check-manifests:
runs-on: ubuntu-22.04
@@ -40,21 +44,13 @@ jobs:
skip: ${{ steps.check-manifests.outputs.skip }}
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@0634a2670c59f64b4a01f0f96f84700a4088b9f0 # v2.12.0
with:
egress-policy: audit
- name: Check if we really need to pin the image
id: check-manifests
env:
FROM_TAG: ${{ inputs.from-tag }}
TO_TAG: pinned
run: |
docker manifest inspect "ghcr.io/neondatabase/build-tools:${FROM_TAG}" > "${FROM_TAG}.json"
docker manifest inspect "ghcr.io/neondatabase/build-tools:${TO_TAG}" > "${TO_TAG}.json"
docker manifest inspect neondatabase/build-tools:${FROM_TAG} > ${FROM_TAG}.json
docker manifest inspect neondatabase/build-tools:${TO_TAG} > ${TO_TAG}.json
if diff "${FROM_TAG}.json" "${TO_TAG}.json"; then
if diff ${FROM_TAG}.json ${TO_TAG}.json; then
skip=true
else
skip=false
@@ -68,36 +64,38 @@ jobs:
# use format(..) to catch both inputs.force = true AND inputs.force = 'true'
if: needs.check-manifests.outputs.skip == 'false' || format('{0}', inputs.force) == 'true'
permissions:
id-token: write # Required for aws/azure login
packages: write # required for pushing to GHCR
runs-on: ubuntu-22.04
uses: ./.github/workflows/_push-to-container-registry.yml
with:
image-map: |
{
"ghcr.io/neondatabase/build-tools:${{ inputs.from-tag }}-bullseye": [
"docker.io/neondatabase/build-tools:pinned-bullseye",
"ghcr.io/neondatabase/build-tools:pinned-bullseye",
"${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}.dkr.ecr.${{ vars.AWS_ECR_REGION }}.amazonaws.com/build-tools:pinned-bullseye",
"${{ vars.AZURE_DEV_REGISTRY_NAME }}.azurecr.io/neondatabase/build-tools:pinned-bullseye"
],
"ghcr.io/neondatabase/build-tools:${{ inputs.from-tag }}-bookworm": [
"docker.io/neondatabase/build-tools:pinned-bookworm",
"docker.io/neondatabase/build-tools:pinned",
"ghcr.io/neondatabase/build-tools:pinned-bookworm",
"ghcr.io/neondatabase/build-tools:pinned",
"${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}.dkr.ecr.${{ vars.AWS_ECR_REGION }}.amazonaws.com/build-tools:pinned-bookworm",
"${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}.dkr.ecr.${{ vars.AWS_ECR_REGION }}.amazonaws.com/build-tools:pinned",
"${{ vars.AZURE_DEV_REGISTRY_NAME }}.azurecr.io/neondatabase/build-tools:pinned-bookworm",
"${{ vars.AZURE_DEV_REGISTRY_NAME }}.azurecr.io/neondatabase/build-tools:pinned"
]
}
aws-region: ${{ vars.AWS_ECR_REGION }}
aws-account-id: "${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}"
aws-role-to-assume: "gha-oidc-neon-admin"
azure-client-id: ${{ vars.AZURE_DEV_CLIENT_ID }}
azure-subscription-id: ${{ vars.AZURE_DEV_SUBSCRIPTION_ID }}
azure-tenant-id: ${{ vars.AZURE_TENANT_ID }}
acr-registry-name: ${{ vars.AZURE_DEV_REGISTRY_NAME }}
secrets: inherit
permissions:
id-token: write # for `azure/login`
steps:
- uses: docker/login-action@v3
with:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
- uses: docker/login-action@v3
with:
registry: 369495373322.dkr.ecr.eu-central-1.amazonaws.com
username: ${{ secrets.AWS_ACCESS_KEY_DEV }}
password: ${{ secrets.AWS_SECRET_KEY_DEV }}
- name: Azure login
uses: azure/login@6c251865b4e6290e7b78be643ea2d005bc51f69a # @v2.1.1
with:
client-id: ${{ secrets.AZURE_DEV_CLIENT_ID }}
tenant-id: ${{ secrets.AZURE_TENANT_ID }}
subscription-id: ${{ secrets.AZURE_DEV_SUBSCRIPTION_ID }}
- name: Login to ACR
run: |
az acr login --name=neoneastus2
- name: Tag build-tools with `${{ env.TO_TAG }}` in Docker Hub, ECR, and ACR
run: |
docker buildx imagetools create -t 369495373322.dkr.ecr.eu-central-1.amazonaws.com/build-tools:${TO_TAG} \
-t neoneastus2.azurecr.io/neondatabase/build-tools:${TO_TAG} \
-t neondatabase/build-tools:${TO_TAG} \
neondatabase/build-tools:${FROM_TAG}

View File

@@ -1,177 +0,0 @@
name: Pre-merge checks
on:
pull_request:
paths:
- .github/workflows/_check-codestyle-python.yml
- .github/workflows/_check-codestyle-rust.yml
- .github/workflows/build-build-tools-image.yml
- .github/workflows/pre-merge-checks.yml
merge_group:
defaults:
run:
shell: bash -euxo pipefail {0}
# No permission for GITHUB_TOKEN by default; the **minimal required** set of permissions should be granted in each job.
permissions: {}
jobs:
meta:
runs-on: ubuntu-22.04
permissions:
contents: read
outputs:
python-changed: ${{ steps.python-src.outputs.any_changed }}
rust-changed: ${{ steps.rust-src.outputs.any_changed }}
branch: ${{ steps.group-metadata.outputs.branch }}
pr-number: ${{ steps.group-metadata.outputs.pr-number }}
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
id: python-src
with:
files: |
.github/workflows/_check-codestyle-python.yml
.github/workflows/build-build-tools-image.yml
.github/workflows/pre-merge-checks.yml
**/**.py
poetry.lock
pyproject.toml
- uses: tj-actions/changed-files@ed68ef82c095e0d48ec87eccea555d944a631a4c # v46.0.5
id: rust-src
with:
files: |
.github/workflows/_check-codestyle-rust.yml
.github/workflows/build-build-tools-image.yml
.github/workflows/pre-merge-checks.yml
**/**.rs
**/Cargo.toml
Cargo.toml
Cargo.lock
- name: PRINT ALL CHANGED FILES FOR DEBUG PURPOSES
env:
PYTHON_CHANGED_FILES: ${{ steps.python-src.outputs.all_changed_files }}
RUST_CHANGED_FILES: ${{ steps.rust-src.outputs.all_changed_files }}
run: |
echo "${PYTHON_CHANGED_FILES}"
echo "${RUST_CHANGED_FILES}"
- name: Merge group metadata
if: ${{ github.event_name == 'merge_group' }}
id: group-metadata
env:
MERGE_QUEUE_REF: ${{ github.event.merge_group.head_ref }}
run: |
echo $MERGE_QUEUE_REF | jq -Rr 'capture("refs/heads/gh-readonly-queue/(?<branch>.*)/pr-(?<pr_number>[0-9]+)-[0-9a-f]{40}") | ["branch=" + .branch, "pr-number=" + .pr_number] | .[]' | tee -a "${GITHUB_OUTPUT}"
build-build-tools-image:
if: |
false
|| needs.meta.outputs.python-changed == 'true'
|| needs.meta.outputs.rust-changed == 'true'
needs: [ meta ]
permissions:
contents: read
packages: write
uses: ./.github/workflows/build-build-tools-image.yml
with:
# Build only one combination to save time
archs: '["x64"]'
debians: '["bookworm"]'
secrets: inherit
check-codestyle-python:
if: needs.meta.outputs.python-changed == 'true'
needs: [ meta, build-build-tools-image ]
permissions:
contents: read
packages: read
uses: ./.github/workflows/_check-codestyle-python.yml
with:
# `-bookworm-x64` suffix should match the combination in `build-build-tools-image`
build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm-x64
secrets: inherit
check-codestyle-rust:
if: needs.meta.outputs.rust-changed == 'true'
needs: [ meta, build-build-tools-image ]
permissions:
contents: read
packages: read
uses: ./.github/workflows/_check-codestyle-rust.yml
with:
# `-bookworm-x64` suffix should match the combination in `build-build-tools-image`
build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm-x64
archs: '["x64"]'
secrets: inherit
# To get items from the merge queue merged into main we need to satisfy "Status checks that are required".
# Currently we require 2 jobs (checks with exact name):
# - conclusion
# - neon-cloud-e2e
conclusion:
# Do not run job on Pull Requests as it interferes with the `conclusion` job from the `build_and_test` workflow
if: always() && github.event_name == 'merge_group'
permissions:
statuses: write # for `github.repos.createCommitStatus(...)`
contents: write
needs:
- meta
- check-codestyle-python
- check-codestyle-rust
runs-on: ubuntu-22.04
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Create fake `neon-cloud-e2e` check
uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
with:
# Retry script for 5XX server errors: https://github.com/actions/github-script#retries
retries: 5
script: |
const { repo, owner } = context.repo;
const targetUrl = `${context.serverUrl}/${owner}/${repo}/actions/runs/${context.runId}`;
await github.rest.repos.createCommitStatus({
owner: owner,
repo: repo,
sha: context.sha,
context: `neon-cloud-e2e`,
state: `success`,
target_url: targetUrl,
description: `fake check for merge queue`,
});
- name: Fail the job if any of the dependencies do not succeed or skipped
run: exit 1
if: |
false
|| (github.event_name == 'merge_group' && needs.meta.outputs.branch != 'main')
|| (needs.check-codestyle-python.result == 'skipped' && needs.meta.outputs.python-changed == 'true')
|| (needs.check-codestyle-rust.result == 'skipped' && needs.meta.outputs.rust-changed == 'true')
|| contains(needs.*.result, 'failure')
|| contains(needs.*.result, 'cancelled')
- name: Add fast-forward label to PR to trigger fast-forward merge
if: >-
${{
always()
&& github.event_name == 'merge_group'
&& contains(fromJSON('["release", "release-proxy", "release-compute"]'), needs.meta.outputs.branch)
}}
env:
GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
run: >-
gh pr edit ${{ needs.meta.outputs.pr-number }} --repo "${GITHUB_REPOSITORY}" --add-label "fast-forward"

View File

@@ -1,112 +0,0 @@
name: Periodic proxy performance test on unit-perf-aws-arm runners
on:
push: # TODO: remove after testing
branches:
- test-proxy-bench # Runs on pushes to test-proxy-bench branch
# schedule:
# * is a special character in YAML so you have to quote this string
# ┌───────────── minute (0 - 59)
# │ ┌───────────── hour (0 - 23)
# │ │ ┌───────────── day of the month (1 - 31)
# │ │ │ ┌───────────── month (1 - 12 or JAN-DEC)
# │ │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
# - cron: '0 5 * * *' # Runs at 5 UTC once a day
workflow_dispatch: # adds an ability to run this manually
defaults:
run:
shell: bash -euo pipefail {0}
concurrency:
group: ${{ github.workflow }}
cancel-in-progress: false
permissions:
contents: read
jobs:
run_periodic_proxybench_test:
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: write
pull-requests: write
runs-on: [ self-hosted, unit-perf-aws-arm ]
timeout-minutes: 60 # 1h timeout
container:
image: ghcr.io/neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
steps:
- name: Checkout proxy-bench Repo
uses: actions/checkout@v4
with:
repository: neondatabase/proxy-bench
path: proxy-bench
- name: Set up the environment which depends on $RUNNER_TEMP on nvme drive
id: set-env
shell: bash -euxo pipefail {0}
run: |
PROXY_BENCH_PATH=$(realpath ./proxy-bench)
{
echo "PROXY_BENCH_PATH=$PROXY_BENCH_PATH"
echo "NEON_DIR=${RUNNER_TEMP}/neon"
echo "NEON_PROXY_PATH=${RUNNER_TEMP}/neon/bin/proxy"
echo "TEST_OUTPUT=${PROXY_BENCH_PATH}/test_output"
echo ""
} >> "$GITHUB_ENV"
- name: Cache poetry deps
uses: actions/cache@v4
with:
path: ~/.cache/pypoetry/virtualenvs
key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-bookworm-${{ hashFiles('poetry.lock') }}
- name: Install Python deps
shell: bash -euxo pipefail {0}
run: ./scripts/pysync
- name: show ulimits
shell: bash -euxo pipefail {0}
run: |
ulimit -a
- name: Run proxy-bench
working-directory: ${{ env.PROXY_BENCH_PATH }}
run: ./run.sh --with-grafana --bare-metal
- name: Ingest Bench Results
if: always()
working-directory: ${{ env.NEON_DIR }}
run: |
mkdir -p $TEST_OUTPUT
python $NEON_DIR/scripts/proxy_bench_results_ingest.py --out $TEST_OUTPUT
- name: Push Metrics to Proxy perf database
shell: bash -euxo pipefail {0}
if: always()
env:
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PROXY_TEST_RESULT_CONNSTR }}"
REPORT_FROM: $TEST_OUTPUT
working-directory: ${{ env.NEON_DIR }}
run: $NEON_DIR/scripts/generate_and_push_perf_report.sh
- name: Notify Failure
if: failure()
run: echo "Proxy bench job failed" && exit 1
- name: Cleanup Test Resources
if: always()
shell: bash -euxo pipefail {0}
run: |
# Cleanup the test resources
if [[ -d "${TEST_OUTPUT}" ]]; then
rm -rf ${TEST_OUTPUT}
fi
if [[ -d "${PROXY_BENCH_PATH}/test_output" ]]; then
rm -rf ${PROXY_BENCH_PATH}/test_output
fi

View File

@@ -1,93 +0,0 @@
name: Random Operations Test
on:
schedule:
# * is a special character in YAML so you have to quote this string
# ┌───────────── minute (0 - 59)
# │ ┌───────────── hour (0 - 23)
# │ │ ┌───────────── day of the month (1 - 31)
# │ │ │ ┌───────────── month (1 - 12 or JAN-DEC)
# │ │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
- cron: '23 */2 * * *' # runs every 2 hours
workflow_dispatch:
inputs:
random_seed:
type: number
description: 'The random seed'
required: false
default: 0
num_operations:
type: number
description: "The number of operations to test"
default: 250
defaults:
run:
shell: bash -euxo pipefail {0}
permissions: {}
env:
DEFAULT_PG_VERSION: 16
PLATFORM: neon-captest-new
AWS_DEFAULT_REGION: eu-central-1
jobs:
run-random-rests:
env:
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
runs-on: small
permissions:
id-token: write
statuses: write
strategy:
fail-fast: false
matrix:
pg-version: [16, 17]
container:
image: ghcr.io/neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Download Neon artifact
uses: ./.github/actions/download
with:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Run tests
uses: ./.github/actions/run-python-test-set
with:
build_type: remote
test_selection: random_ops
run_in_parallel: false
extra_params: -m remote_cluster
pg_version: ${{ matrix.pg-version }}
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
NEON_API_KEY: ${{ secrets.NEON_STAGING_API_KEY }}
RANDOM_SEED: ${{ inputs.random_seed }}
NUM_OPERATIONS: ${{ inputs.num_operations }}
- name: Create Allure report
if: ${{ !cancelled() }}
id: create-allure-report
uses: ./.github/actions/allure-report-generate
with:
store-test-results-into-db: true
aws-oidc-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}

View File

@@ -1,46 +0,0 @@
name: Regenerate Postgres Settings
on:
pull_request:
types:
- opened
- synchronize
- reopened
paths:
- pgxn/neon/**.c
- vendor/postgres-v*
- vendor/revisions.json
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref }}
cancel-in-progress: true
permissions:
pull-requests: write
jobs:
regenerate-pg-settings:
runs-on: ubuntu-22.04
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Add comment
uses: thollander/actions-comment-pull-request@65f9e5c9a1f2cd378bd74b2e057c9736982a8e74 # v3
with:
comment-tag: ${{ github.job }}
pr-number: ${{ github.event.number }}
message: |
If this PR added a GUC in the Postgres fork or `neon` extension,
please regenerate the Postgres settings in the `cloud` repo:
```
make NEON_WORKDIR=path/to/neon/checkout \
-C goapp/internal/shareddomain/postgres generate
```
If you're an external contributor, a Neon employee will assist in
making sure this step is done.

View File

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

View File

@@ -22,12 +22,7 @@ jobs:
runs-on: ubuntu-22.04
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: neondatabase/dev-actions/release-pr-notify@483a843f2a8bcfbdc4c69d27630528a3ddc4e14b # main
- uses: neondatabase/dev-actions/release-pr-notify@main
with:
slack-token: ${{ secrets.SLACK_BOT_TOKEN }}
slack-channel-id: ${{ vars.SLACK_UPCOMING_RELEASE_CHANNEL_ID || 'C05QQ9J1BRC' }} # if not set, then `#test-release-notifications`

View File

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

View File

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

View File

@@ -1,34 +1,20 @@
name: Create release PR
name: Create Release Branch
on:
schedule:
# It should be kept in sync with if-condition in jobs
- cron: '0 6 * * MON' # Storage release
- cron: '0 6 * * THU' # Proxy release
workflow_dispatch:
inputs:
component:
description: "Component to release"
required: true
type: choice
options:
- compute
- proxy
- storage
cherry-pick:
description: "Commits to cherry-pick (space separated, makes this a hotfix based on previous release)"
create-storage-release-branch:
type: boolean
description: 'Create Storage release PR'
required: false
type: string
default: ''
workflow_call:
inputs:
component:
description: "Component to release"
required: true
type: string
cherry-pick:
description: "Commits to cherry-pick (space separated, makes this a hotfix based on previous release)"
create-proxy-release-branch:
type: boolean
description: 'Create Proxy release PR'
required: false
type: string
default: ''
# No permission for GITHUB_TOKEN by default; the **minimal required** set of permissions should be granted in each job.
permissions: {}
@@ -38,31 +24,84 @@ defaults:
shell: bash -euo pipefail {0}
jobs:
create-release-pr:
create-storage-release-branch:
if: ${{ github.event.schedule == '0 6 * * MON' || format('{0}', inputs.create-storage-release-branch) == 'true' }}
runs-on: ubuntu-22.04
permissions:
contents: write
contents: write # for `git push`
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Check out code
uses: actions/checkout@v4
with:
ref: main
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
fetch-depth: 0
- name: Set environment variables
run: |
echo "RELEASE_DATE=$(date +'%Y-%m-%d')" | tee -a $GITHUB_ENV
echo "RELEASE_BRANCH=rc/$(date +'%Y-%m-%d')" | tee -a $GITHUB_ENV
- name: Configure git
run: |
git config user.name "github-actions[bot]"
git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
- name: Create release branch
run: git checkout -b $RELEASE_BRANCH
- name: Create release PR
uses: neondatabase/dev-actions/release-pr@290dec821d86fa8a93f019e8c69720f5865b5677
with:
component: ${{ inputs.component }}
cherry-pick: ${{ inputs.cherry-pick }}
env:
GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
- name: Push new branch
run: git push origin $RELEASE_BRANCH
- name: Create pull request into release
env:
GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
run: |
TITLE="Storage & Compute release ${RELEASE_DATE}"
cat << EOF > body.md
## ${TITLE}
**Please merge this Pull Request using 'Create a merge commit' button**
EOF
gh pr create --title "${TITLE}" \
--body-file "body.md" \
--head "${RELEASE_BRANCH}" \
--base "release"
create-proxy-release-branch:
if: ${{ github.event.schedule == '0 6 * * THU' || format('{0}', inputs.create-proxy-release-branch) == 'true' }}
runs-on: ubuntu-22.04
permissions:
contents: write # for `git push`
steps:
- name: Check out code
uses: actions/checkout@v4
with:
ref: main
- name: Set environment variables
run: |
echo "RELEASE_DATE=$(date +'%Y-%m-%d')" | tee -a $GITHUB_ENV
echo "RELEASE_BRANCH=rc/proxy/$(date +'%Y-%m-%d')" | tee -a $GITHUB_ENV
- name: Create release branch
run: git checkout -b $RELEASE_BRANCH
- name: Push new branch
run: git push origin $RELEASE_BRANCH
- name: Create pull request into release
env:
GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
run: |
TITLE="Proxy release ${RELEASE_DATE}"
cat << EOF > body.md
## ${TITLE}
**Please merge this Pull Request using 'Create a merge commit' button**
EOF
gh pr create --title "${TITLE}" \
--body-file "body.md" \
--head "${RELEASE_BRANCH}" \
--base "release-proxy"

View File

@@ -1,71 +0,0 @@
name: Report Workflow Stats Batch
on:
schedule:
- cron: '*/15 * * * *'
- cron: '25 0 * * *'
- cron: '25 1 * * 6'
permissions:
contents: read
jobs:
gh-workflow-stats-batch-2h:
name: GitHub Workflow Stats Batch 2 hours
if: github.event.schedule == '*/15 * * * *'
runs-on: ubuntu-22.04
permissions:
actions: read
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Export Workflow Run for the past 2 hours
uses: neondatabase/gh-workflow-stats-action@701b1f202666d0b82e67b4d387e909af2b920127 # v0.2.2
with:
db_uri: ${{ secrets.GH_REPORT_STATS_DB_RW_CONNSTR }}
db_table: "gh_workflow_stats_neon"
gh_token: ${{ secrets.GITHUB_TOKEN }}
duration: '2h'
gh-workflow-stats-batch-48h:
name: GitHub Workflow Stats Batch 48 hours
if: github.event.schedule == '25 0 * * *'
runs-on: ubuntu-22.04
permissions:
actions: read
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Export Workflow Run for the past 48 hours
uses: neondatabase/gh-workflow-stats-action@701b1f202666d0b82e67b4d387e909af2b920127 # v0.2.2
with:
db_uri: ${{ secrets.GH_REPORT_STATS_DB_RW_CONNSTR }}
db_table: "gh_workflow_stats_neon"
gh_token: ${{ secrets.GITHUB_TOKEN }}
duration: '48h'
gh-workflow-stats-batch-30d:
name: GitHub Workflow Stats Batch 30 days
if: github.event.schedule == '25 1 * * 6'
runs-on: ubuntu-22.04
permissions:
actions: read
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Export Workflow Run for the past 30 days
uses: neondatabase/gh-workflow-stats-action@701b1f202666d0b82e67b4d387e909af2b920127 # v0.2.2
with:
db_uri: ${{ secrets.GH_REPORT_STATS_DB_RW_CONNSTR }}
db_table: "gh_workflow_stats_neon"
gh_token: ${{ secrets.GITHUB_TOKEN }}
duration: '720h'

View File

@@ -5,13 +5,6 @@ on:
types:
- ready_for_review
workflow_call:
inputs:
github-event-name:
type: string
required: true
github-event-json:
type: string
required: true
defaults:
run:
@@ -22,23 +15,11 @@ env:
E2E_CONCURRENCY_GROUP: ${{ github.repository }}-e2e-tests-${{ github.ref_name }}-${{ github.ref_name == 'main' && github.sha || 'anysha' }}
jobs:
check-permissions:
if: ${{ !contains(github.event.pull_request.labels.*.name, 'run-no-ci') }}
uses: ./.github/workflows/check-permissions.yml
with:
github-event-name: ${{ inputs.github-event-name || github.event_name }}
cancel-previous-e2e-tests:
needs: [ check-permissions ]
if: github.event_name == 'pull_request'
runs-on: ubuntu-22.04
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@0634a2670c59f64b4a01f0f96f84700a4088b9f0 # v2.12.0
with:
egress-policy: audit
- name: Cancel previous e2e-tests runs for this PR
env:
GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
@@ -47,37 +28,45 @@ jobs:
run cancel-previous-in-concurrency-group.yml \
--field concurrency_group="${{ env.E2E_CONCURRENCY_GROUP }}"
meta:
uses: ./.github/workflows/_meta.yml
with:
github-event-name: ${{ inputs.github-event-name || github.event_name }}
github-event-json: ${{ inputs.github-event-json || toJSON(github.event) }}
tag:
runs-on: ubuntu-22.04
outputs:
build-tag: ${{ steps.build-tag.outputs.tag }}
steps:
# Need `fetch-depth: 0` to count the number of commits in the branch
- uses: actions/checkout@v4
with:
fetch-depth: 0
- name: Get build tag
env:
GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
CURRENT_BRANCH: ${{ github.head_ref || github.ref_name }}
CURRENT_SHA: ${{ github.event.pull_request.head.sha || github.sha }}
run: |
if [[ "$GITHUB_REF_NAME" == "main" ]]; then
echo "tag=$(git rev-list --count HEAD)" | tee -a $GITHUB_OUTPUT
elif [[ "$GITHUB_REF_NAME" == "release" ]]; then
echo "tag=release-$(git rev-list --count HEAD)" | tee -a $GITHUB_OUTPUT
elif [[ "$GITHUB_REF_NAME" == "release-proxy" ]]; then
echo "tag=release-proxy-$(git rev-list --count HEAD)" >> $GITHUB_OUTPUT
else
echo "GITHUB_REF_NAME (value '$GITHUB_REF_NAME') is not set to either 'main' or 'release'"
BUILD_AND_TEST_RUN_ID=$(gh run list -b $CURRENT_BRANCH -c $CURRENT_SHA -w 'Build and Test' -L 1 --json databaseId --jq '.[].databaseId')
echo "tag=$BUILD_AND_TEST_RUN_ID" | tee -a $GITHUB_OUTPUT
fi
id: build-tag
trigger-e2e-tests:
needs: [ meta ]
needs: [ tag ]
runs-on: ubuntu-22.04
env:
EVENT_ACTION: ${{ github.event.action }}
GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
TAG: >-
${{
contains(fromJSON('["compute-release", "compute-rc-pr"]'), needs.meta.outputs.run-kind)
&& needs.meta.outputs.previous-storage-release
|| needs.meta.outputs.build-tag
}}
COMPUTE_TAG: >-
${{
contains(fromJSON('["storage-release", "storage-rc-pr", "proxy-release", "proxy-rc-pr"]'), needs.meta.outputs.run-kind)
&& needs.meta.outputs.previous-compute-release
|| needs.meta.outputs.build-tag
}}
TAG: ${{ needs.tag.outputs.build-tag }}
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@0634a2670c59f64b4a01f0f96f84700a4088b9f0 # v2.12.0
with:
egress-policy: audit
- name: Wait for `push-{neon,compute}-image-dev` job to finish
- name: Wait for `promote-images` job to finish
# It's important to have a timeout here, the script in the step can run infinitely
timeout-minutes: 60
run: |
@@ -88,20 +77,20 @@ jobs:
# For PRs we use the run id as the tag
BUILD_AND_TEST_RUN_ID=${TAG}
while true; do
gh run --repo ${GITHUB_REPOSITORY} view ${BUILD_AND_TEST_RUN_ID} --json jobs --jq '[.jobs[] | select((.name | startswith("push-neon-image-dev")) or (.name | startswith("push-compute-image-dev"))) | {"name": .name, "conclusion": .conclusion, "url": .url}]' > jobs.json
if [ $(jq '[.[] | select(.conclusion == "success")] | length' jobs.json) -eq 2 ]; then
break
fi
jq -c '.[]' jobs.json | while read -r job; do
case $(echo $job | jq .conclusion) in
failure | cancelled | skipped)
echo "The '$(echo $job | jq .name)' job didn't succeed: '$(echo $job | jq .conclusion)'. See log in '$(echo $job | jq .url)' Exiting..."
exit 1
;;
esac
done
echo "The 'push-{neon,compute}-image-dev' jobs haven't succeeded yet. Waiting..."
sleep 60
conclusion=$(gh run --repo ${GITHUB_REPOSITORY} view ${BUILD_AND_TEST_RUN_ID} --json jobs --jq '.jobs[] | select(.name == "promote-images") | .conclusion')
case "$conclusion" in
success)
break
;;
failure | cancelled | skipped)
echo "The 'promote-images' job didn't succeed: '${conclusion}'. Exiting..."
exit 1
;;
*)
echo "The 'promote-images' hasn't succeed yet. Waiting..."
sleep 60
;;
esac
done
- name: Set e2e-platforms
@@ -113,17 +102,12 @@ jobs:
# Default set of platforms to run e2e tests on
platforms='["docker", "k8s"]'
# If a PR changes anything that affects computes, add k8s-neonvm to the list of platforms.
# If the PR changes vendor/, pgxn/ or libs/vm_monitor/ directories, or Dockerfile.compute-node, add k8s-neonvm to the list of platforms.
# If the workflow run is not a pull request, add k8s-neonvm to the list.
if [ "$GITHUB_EVENT_NAME" == "pull_request" ]; then
for f in $(gh api "/repos/${GITHUB_REPOSITORY}/pulls/${PR_NUMBER}/files" --paginate --jq '.[].filename'); do
case "$f" in
# List of directories that contain code which affect compute images.
#
# This isn't exhaustive, just the paths that are most directly compute-related.
# For example, compute_ctl also depends on libs/utils, but we don't trigger
# an e2e run on that.
vendor/*|pgxn/*|compute_tools/*|libs/vm_monitor/*|compute/compute-node.Dockerfile)
vendor/*|pgxn/*|libs/vm_monitor/*|Dockerfile.compute-node)
platforms=$(echo "${platforms}" | jq --compact-output '. += ["k8s-neonvm"] | unique')
;;
*)
@@ -158,6 +142,6 @@ jobs:
--raw-field "commit_hash=$COMMIT_SHA" \
--raw-field "remote_repo=${GITHUB_REPOSITORY}" \
--raw-field "storage_image_tag=${TAG}" \
--raw-field "compute_image_tag=${COMPUTE_TAG}" \
--raw-field "compute_image_tag=${TAG}" \
--raw-field "concurrency_group=${E2E_CONCURRENCY_GROUP}" \
--raw-field "e2e-platforms=${E2E_PLATFORMS}"

14
.gitignore vendored
View File

@@ -1,21 +1,15 @@
/artifact_cache
/build
/pg_install
/target
/tmp_check
/tmp_check_cli
__pycache__/
test_output/
neon_previous/
.vscode
.idea
*.swp
tags
neon.iml
/.neon
/integration_tests/.neon
compaction-suite-results.*
docker-compose/docker-compose-parallel.yml
# Coverage
*.profraw
@@ -26,14 +20,6 @@ docker-compose/docker-compose-parallel.yml
*.o
*.so
*.Po
*.pid
# pgindent typedef lists
*.list
# Node
**/node_modules/
# various files for local testing
/proxy/.subzero
local_proxy.json

8
.gitmodules vendored
View File

@@ -1,16 +1,16 @@
[submodule "vendor/postgres-v14"]
path = vendor/postgres-v14
url = ../postgres.git
url = https://github.com/neondatabase/postgres.git
branch = REL_14_STABLE_neon
[submodule "vendor/postgres-v15"]
path = vendor/postgres-v15
url = ../postgres.git
url = https://github.com/neondatabase/postgres.git
branch = REL_15_STABLE_neon
[submodule "vendor/postgres-v16"]
path = vendor/postgres-v16
url = ../postgres.git
url = https://github.com/neondatabase/postgres.git
branch = REL_16_STABLE_neon
[submodule "vendor/postgres-v17"]
path = vendor/postgres-v17
url = ../postgres.git
url = https://github.com/neondatabase/postgres.git
branch = REL_17_STABLE_neon

View File

@@ -1,29 +1,13 @@
# Autoscaling
/libs/vm_monitor/ @neondatabase/autoscaling
# DevProd & PerfCorr
/.github/ @neondatabase/developer-productivity @neondatabase/performance-correctness
# Compute
/pgxn/ @neondatabase/compute
/vendor/ @neondatabase/compute
/compute/ @neondatabase/compute
/compute_tools/ @neondatabase/compute
# Proxy
/libs/proxy/ @neondatabase/proxy
/proxy/ @neondatabase/proxy
# Storage
/pageserver/ @neondatabase/storage
/safekeeper/ @neondatabase/storage
/compute_tools/ @neondatabase/control-plane @neondatabase/compute
/storage_controller @neondatabase/storage
/storage_scrubber @neondatabase/storage
/libs/pageserver_api/ @neondatabase/storage
/libs/postgres_ffi/ @neondatabase/compute @neondatabase/storage
/libs/remote_storage/ @neondatabase/storage
/libs/safekeeper_api/ @neondatabase/storage
# Shared
/libs/vm_monitor/ @neondatabase/autoscaling
/pageserver/ @neondatabase/storage
/pgxn/ @neondatabase/compute
/pgxn/neon/ @neondatabase/compute @neondatabase/storage
/libs/compute_api/ @neondatabase/compute @neondatabase/control-plane
/libs/postgres_ffi/ @neondatabase/compute @neondatabase/storage
/proxy/ @neondatabase/proxy
/safekeeper/ @neondatabase/storage
/vendor/ @neondatabase/compute

3869
Cargo.lock generated

File diff suppressed because it is too large Load Diff

View File

@@ -8,30 +8,22 @@ members = [
"pageserver/compaction",
"pageserver/ctl",
"pageserver/client",
"pageserver/client_grpc",
"pageserver/pagebench",
"pageserver/page_api",
"proxy",
"safekeeper",
"safekeeper/client",
"storage_broker",
"storage_controller",
"storage_controller/client",
"storage_scrubber",
"workspace_hack",
"libs/compute_api",
"libs/http-utils",
"libs/pageserver_api",
"libs/postgres_ffi",
"libs/postgres_ffi_types",
"libs/postgres_versioninfo",
"libs/safekeeper_api",
"libs/desim",
"libs/neon-shmem",
"libs/utils",
"libs/consumption_metrics",
"libs/postgres_backend",
"libs/posthog_client_lite",
"libs/pq_proto",
"libs/tenant_size_model",
"libs/metrics",
@@ -41,60 +33,52 @@ members = [
"libs/postgres_ffi/wal_craft",
"libs/vm_monitor",
"libs/walproposer",
"libs/wal_decoder",
"libs/postgres_initdb",
"libs/proxy/json",
"libs/proxy/postgres-protocol2",
"libs/proxy/postgres-types2",
"libs/proxy/tokio-postgres2",
"endpoint_storage",
"pgxn/neon/communicator",
"proxy/subzero_core",
]
[workspace.package]
edition = "2024"
edition = "2021"
license = "Apache-2.0"
## All dependency versions, used in the project
[workspace.dependencies]
ahash = "0.8"
anyhow = { version = "1.0", features = ["backtrace"] }
arc-swap = "1.7"
arc-swap = "1.6"
async-compression = { version = "0.4.0", features = ["tokio", "gzip", "zstd"] }
atomic-take = "1.1.0"
azure_core = { version = "0.19", default-features = false, features = ["enable_reqwest_rustls", "hmac_rust"] }
azure_identity = { version = "0.19", default-features = false, features = ["enable_reqwest_rustls"] }
azure_storage = { version = "0.19", default-features = false, features = ["enable_reqwest_rustls"] }
azure_storage_blobs = { version = "0.19", default-features = false, features = ["enable_reqwest_rustls"] }
flate2 = "1.0.26"
assert-json-diff = "2"
async-stream = "0.3"
async-trait = "0.1"
aws-config = { version = "1.5", default-features = false, features=["rustls", "sso"] }
aws-sdk-s3 = "1.52"
aws-sdk-iam = "1.46.0"
aws-sdk-kms = "1.47.0"
aws-config = { version = "1.3", default-features = false, features=["rustls"] }
aws-sdk-s3 = "1.26"
aws-sdk-iam = "1.15.0"
aws-smithy-async = { version = "1.2.1", default-features = false, features=["rt-tokio"] }
aws-smithy-types = "1.2"
aws-smithy-types = "1.1.9"
aws-credential-types = "1.2.0"
aws-sigv4 = { version = "1.2", features = ["sign-http"] }
aws-types = "1.3"
axum = { version = "0.8.1", features = ["ws"] }
axum-extra = { version = "0.10.0", features = ["typed-header", "query"] }
base64 = "0.22"
aws-sigv4 = { version = "1.2.1", features = ["sign-http"] }
aws-types = "1.2.0"
axum = { version = "0.6.20", features = ["ws"] }
base64 = "0.13.0"
bincode = "1.3"
bindgen = "0.71"
bindgen = "0.70"
bit_field = "0.10.2"
bstr = "1.0"
byteorder = "1.4"
bytes = "1.9"
bytes = "1.0"
camino = "1.1.6"
cfg-if = "1.0.0"
cron = "0.15"
chrono = { version = "0.4", default-features = false, features = ["clock"] }
clap = { version = "4.0", features = ["derive", "env"] }
clashmap = { version = "1.0", features = ["raw-api"] }
clap = { version = "4.0", features = ["derive"] }
comfy-table = "7.1"
const_format = "0.2"
crc32c = "0.6"
diatomic-waker = { version = "0.2.3" }
crossbeam-deque = "0.8.5"
crossbeam-utils = "0.8.5"
dashmap = { version = "5.5.0", features = ["raw-api"] }
either = "1.8"
enum-map = "2.4.2"
enumset = "1.0.12"
@@ -105,211 +89,176 @@ futures = "0.3"
futures-core = "0.3"
futures-util = "0.3"
git-version = "0.3"
governor = "0.8"
hashbrown = "0.14"
hashlink = "0.9.1"
hdrhistogram = "7.5.2"
hex = "0.4"
hex-literal = "0.4"
hmac = "0.12.1"
hostname = "0.4"
hostname = "0.3.1"
http = {version = "1.1.0", features = ["std"]}
http-types = { version = "2", default-features = false }
http-body-util = "0.1.2"
humantime = "2.2"
humantime = "2.1"
humantime-serde = "1.1.1"
hyper0 = { package = "hyper", version = "0.14" }
hyper = "1.4"
hyper-util = "0.1"
tokio-tungstenite = "0.21.0"
indexmap = { version = "2", features = ["serde"] }
hyper = "0.14"
tokio-tungstenite = "0.20.0"
indexmap = "2"
indoc = "2"
ipnet = "2.10.0"
inotify = "0.10.2"
ipnet = "2.9.0"
itertools = "0.10"
itoa = "1.0.11"
jemalloc_pprof = { version = "0.7", features = ["symbolize", "flamegraph"] }
jsonwebtoken = "9"
lasso = "0.7"
libc = "0.2"
lock_api = "0.4.13"
md5 = "0.7.0"
measured = { version = "0.0.22", features=["lasso"] }
measured-process = { version = "0.0.22" }
memoffset = "0.9"
nix = { version = "0.30.1", features = ["dir", "fs", "mman", "process", "socket", "signal", "poll"] }
# Do not update to >= 7.0.0, at least. The update will have a significant impact
# on compute startup metrics (start_postgres_ms), >= 25% degradation.
memoffset = "0.8"
nix = { version = "0.27", features = ["dir", "fs", "process", "socket", "signal", "poll"] }
notify = "6.0.0"
num_cpus = "1.15"
num-traits = "0.2.19"
num-traits = "0.2.15"
once_cell = "1.13"
opentelemetry = "0.30"
opentelemetry_sdk = "0.30"
opentelemetry-otlp = { version = "0.30", default-features = false, features = ["http-proto", "trace", "http", "reqwest-blocking-client"] }
opentelemetry-semantic-conventions = "0.30"
opentelemetry = "0.20.0"
opentelemetry-otlp = { version = "0.13.0", default-features=false, features = ["http-proto", "trace", "http", "reqwest-client"] }
opentelemetry-semantic-conventions = "0.12.0"
parking_lot = "0.12"
parquet = { version = "53", default-features = false, features = ["zstd"] }
parquet_derive = "53"
pbkdf2 = { version = "0.12.1", features = ["simple", "std"] }
pem = "3.0.3"
pin-project-lite = "0.2"
pprof = { version = "0.14", features = ["criterion", "flamegraph", "frame-pointer", "prost-codec"] }
procfs = "0.16"
prometheus = {version = "0.13", default-features=false, features = ["process"]} # removes protobuf dependency
prost = "0.13.5"
prost-types = "0.13.5"
rand = "0.9"
# Remove after p256 is updated to 0.14.
rand_core = "=0.6"
redis = { version = "0.29.2", features = ["tokio-rustls-comp", "keep-alive"] }
prost = "0.11"
rand = "0.8"
redis = { version = "0.25.2", features = ["tokio-rustls-comp", "keep-alive"] }
regex = "1.10.2"
reqwest = { version = "0.12", default-features = false, features = ["rustls-tls"] }
reqwest-tracing = { version = "0.5", features = ["opentelemetry_0_30"] }
reqwest-middleware = "0.4"
reqwest-retry = "0.7"
reqwest-tracing = { version = "0.5", features = ["opentelemetry_0_20"] }
reqwest-middleware = "0.3.0"
reqwest-retry = "0.5"
routerify = "3"
rpds = "0.13"
rustc-hash = "2.1.1"
rustls = { version = "0.23.16", default-features = false }
rustc-hash = "1.1.0"
rustls = "0.22"
rustls-pemfile = "2"
rustls-pki-types = "1.11"
rustls-split = "0.3"
scopeguard = "1.1"
sysinfo = "0.29.2"
sd-notify = "0.4.1"
send-future = "0.1.0"
sentry = { version = "0.37", default-features = false, features = ["backtrace", "contexts", "panic", "rustls", "reqwest" ] }
sentry = { version = "0.32", default-features = false, features = ["backtrace", "contexts", "panic", "rustls", "reqwest" ] }
serde = { version = "1.0", features = ["derive"] }
serde_json = "1"
serde_path_to_error = "0.1"
serde_with = { version = "3", features = [ "base64" ] }
serde_with = "2.0"
serde_assert = "0.5.0"
serde_repr = "0.1.20"
sha2 = "0.10.2"
signal-hook = "0.3"
smallvec = "1.11"
smol_str = { version = "0.2.0", features = ["serde"] }
socket2 = "0.5"
spki = "0.7.3"
strum = "0.26"
strum_macros = "0.26"
"subtle" = "2.5.0"
svg_fmt = "0.4.3"
sync_wrapper = "0.1.2"
tar = "0.4"
task-local-extensions = "0.1.4"
test-context = "0.3"
thiserror = "1.0"
tikv-jemallocator = { version = "0.6", features = ["profiling", "stats", "unprefixed_malloc_on_supported_platforms"] }
tikv-jemalloc-ctl = { version = "0.6", features = ["stats"] }
tokio = { version = "1.43.1", features = ["macros"] }
tikv-jemallocator = "0.5"
tikv-jemalloc-ctl = "0.5"
tokio = { version = "1.17", features = ["macros"] }
tokio-epoll-uring = { git = "https://github.com/neondatabase/tokio-epoll-uring.git" , branch = "main" }
tokio-io-timeout = "1.2.0"
tokio-postgres-rustls = "0.12.0"
tokio-rustls = { version = "0.26.0", default-features = false, features = ["tls12", "ring"]}
tokio-stream = { version = "0.1", features = ["sync"] }
tokio-postgres-rustls = "0.11.0"
tokio-rustls = "0.25"
tokio-stream = "0.1"
tokio-tar = "0.3"
tokio-util = { version = "0.7.10", features = ["io", "io-util", "rt"] }
tokio-util = { version = "0.7.10", features = ["io", "rt"] }
toml = "0.8"
toml_edit = "0.22"
tonic = { version = "0.13.1", default-features = false, features = ["channel", "codegen", "gzip", "prost", "router", "server", "tls-ring", "tls-native-roots", "zstd"] }
tonic-reflection = { version = "0.13.1", features = ["server"] }
tower = { version = "0.5.2", default-features = false }
tower-http = { version = "0.6.2", features = ["auth", "request-id", "trace"] }
tower-otel = { version = "0.6", features = ["axum"] }
tower-service = "0.3.3"
tonic = {version = "0.9", features = ["tls", "tls-roots"]}
tower-service = "0.3.2"
tracing = "0.1"
tracing-error = "0.2"
tracing-log = "0.2"
tracing-opentelemetry = "0.31"
tracing-serde = "0.2.0"
tracing-error = "0.2.0"
tracing-opentelemetry = "0.21.0"
tracing-subscriber = { version = "0.3", default-features = false, features = ["smallvec", "fmt", "tracing-log", "std", "env-filter", "json"] }
tracing-appender = "0.2.3"
try-lock = "0.2.5"
test-log = { version = "0.2.17", default-features = false, features = ["log"] }
twox-hash = { version = "1.6.3", default-features = false }
typed-json = "0.1"
url = "2.2"
urlencoding = "2.1"
uuid = { version = "1.6.1", features = ["v4", "v7", "serde"] }
walkdir = "2.3.2"
rustls-native-certs = "0.8"
rustls-native-certs = "0.7"
x509-parser = "0.15"
whoami = "1.5.1"
zerocopy = { version = "0.8", features = ["derive", "simd"] }
json-structural-diff = { version = "0.2.0" }
x509-cert = { version = "0.2.5" }
## TODO replace this with tracing
env_logger = "0.11"
env_logger = "0.10"
log = "0.4"
## Libraries from neondatabase/ git forks, ideally with changes to be upstreamed
postgres = { git = "https://github.com/neondatabase/rust-postgres.git", branch = "neon" }
postgres-protocol = { git = "https://github.com/neondatabase/rust-postgres.git", branch = "neon" }
postgres-types = { git = "https://github.com/neondatabase/rust-postgres.git", branch = "neon" }
tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", branch = "neon" }
## Azure SDK crates
azure_core = { git = "https://github.com/neondatabase/azure-sdk-for-rust.git", branch = "neon", default-features = false, features = ["enable_reqwest_rustls", "hmac_rust"] }
azure_identity = { git = "https://github.com/neondatabase/azure-sdk-for-rust.git", branch = "neon", default-features = false, features = ["enable_reqwest_rustls"] }
azure_storage = { git = "https://github.com/neondatabase/azure-sdk-for-rust.git", branch = "neon", default-features = false, features = ["enable_reqwest_rustls"] }
azure_storage_blobs = { git = "https://github.com/neondatabase/azure-sdk-for-rust.git", branch = "neon", default-features = false, features = ["enable_reqwest_rustls"] }
# We want to use the 'neon' branch for these, but there's currently one
# incompatible change on the branch. See:
#
# - PR #8076 which contained changes that depended on the new changes in
# the rust-postgres crate, and
# - PR #8654 which reverted those changes and made the code in proxy incompatible
# with the tip of the 'neon' branch again.
#
# When those proxy changes are re-applied (see PR #8747), we can switch using
# the tip of the 'neon' branch again.
postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev = "20031d7a9ee1addeae6e0968e3899ae6bf01cee2" }
postgres-protocol = { git = "https://github.com/neondatabase/rust-postgres.git", rev = "20031d7a9ee1addeae6e0968e3899ae6bf01cee2" }
postgres-types = { git = "https://github.com/neondatabase/rust-postgres.git", rev = "20031d7a9ee1addeae6e0968e3899ae6bf01cee2" }
tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev = "20031d7a9ee1addeae6e0968e3899ae6bf01cee2" }
## Local libraries
compute_api = { version = "0.1", path = "./libs/compute_api/" }
consumption_metrics = { version = "0.1", path = "./libs/consumption_metrics/" }
desim = { version = "0.1", path = "./libs/desim" }
endpoint_storage = { version = "0.0.1", path = "./endpoint_storage/" }
http-utils = { version = "0.1", path = "./libs/http-utils/" }
metrics = { version = "0.1", path = "./libs/metrics/" }
neon-shmem = { version = "0.1", path = "./libs/neon-shmem/" }
pageserver = { path = "./pageserver" }
pageserver_api = { version = "0.1", path = "./libs/pageserver_api/" }
pageserver_client = { path = "./pageserver/client" }
pageserver_client_grpc = { path = "./pageserver/client_grpc" }
pageserver_compaction = { version = "0.1", path = "./pageserver/compaction/" }
pageserver_page_api = { path = "./pageserver/page_api" }
postgres_backend = { version = "0.1", path = "./libs/postgres_backend/" }
postgres_connection = { version = "0.1", path = "./libs/postgres_connection/" }
postgres_ffi = { version = "0.1", path = "./libs/postgres_ffi/" }
postgres_ffi_types = { version = "0.1", path = "./libs/postgres_ffi_types/" }
postgres_versioninfo = { version = "0.1", path = "./libs/postgres_versioninfo/" }
postgres_initdb = { path = "./libs/postgres_initdb" }
posthog_client_lite = { version = "0.1", path = "./libs/posthog_client_lite" }
pq_proto = { version = "0.1", path = "./libs/pq_proto/" }
remote_storage = { version = "0.1", path = "./libs/remote_storage/" }
safekeeper_api = { version = "0.1", path = "./libs/safekeeper_api" }
safekeeper_client = { path = "./safekeeper/client" }
desim = { version = "0.1", path = "./libs/desim" }
storage_broker = { version = "0.1", path = "./storage_broker/" } # Note: main broker code is inside the binary crate, so linking with the library shouldn't be heavy.
storage_controller_client = { path = "./storage_controller/client" }
tenant_size_model = { version = "0.1", path = "./libs/tenant_size_model/" }
tracing-utils = { version = "0.1", path = "./libs/tracing-utils/" }
utils = { version = "0.1", path = "./libs/utils/" }
vm_monitor = { version = "0.1", path = "./libs/vm_monitor/" }
wal_decoder = { version = "0.1", path = "./libs/wal_decoder" }
walproposer = { version = "0.1", path = "./libs/walproposer/" }
## Common library dependency
workspace_hack = { version = "0.1", path = "./workspace_hack/" }
## Build dependencies
cbindgen = "0.29.0"
criterion = "0.5.1"
rcgen = "0.13"
rcgen = "0.12"
rstest = "0.18"
camino-tempfile = "1.0.2"
tonic-build = "0.13.1"
tonic-build = "0.9"
[patch.crates-io]
# Needed to get `tokio-postgres-rustls` to depend on our fork.
tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", branch = "neon" }
tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", rev = "20031d7a9ee1addeae6e0968e3899ae6bf01cee2" }
################# Binary contents sections
[profile.release]
# This is useful for profiling and, to some extent, debug.
# Besides, debug info should not affect the performance.
#
# NB: we also enable frame pointers for improved profiling, see .cargo/config.toml.
debug = true
# disable debug symbols for all packages except this one to decrease binaries size

View File

@@ -2,46 +2,13 @@
### 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=ghcr.io/neondatabase
ARG REPOSITORY=neondatabase
ARG IMAGE=build-tools
ARG TAG=pinned
ARG DEBIAN_VERSION=bookworm
ARG DEBIAN_FLAVOR=${DEBIAN_VERSION}-slim
ARG DEFAULT_PG_VERSION=17
ARG STABLE_PG_VERSION=16
# Here are the INDEX DIGESTS for the images we use.
# You can get them following next steps for now:
# 1. Get an authentication token from DockerHub:
# TOKEN=$(curl -s "https://auth.docker.io/token?service=registry.docker.io&scope=repository:library/debian:pull" | jq -r .token)
# 2. Using that token, query index for the given tag:
# curl -s -H "Authorization: Bearer $TOKEN" \
# -H "Accept: application/vnd.docker.distribution.manifest.list.v2+json" \
# "https://registry.hub.docker.com/v2/library/debian/manifests/bullseye-slim" \
# -I | grep -i docker-content-digest
# 3. As a next step, TODO(fedordikarev): create script and schedule workflow to run these checks
# and updates on regular bases and in automated way.
ARG BOOKWORM_SLIM_SHA=sha256:40b107342c492725bc7aacbe93a49945445191ae364184a6d24fedb28172f6f7
ARG BULLSEYE_SLIM_SHA=sha256:e831d9a884d63734fe3dd9c491ed9a5a3d4c6a6d32c5b14f2067357c49b0b7e1
# Here we use ${var/search/replace} syntax, to check
# if base image is one of the images, we pin image index for.
# If var will match one the known images, we will replace it with the known sha.
# If no match, than value will be unaffected, and will process with no-pinned image.
ARG BASE_IMAGE_SHA=debian:${DEBIAN_FLAVOR}
ARG BASE_IMAGE_SHA=${BASE_IMAGE_SHA/debian:bookworm-slim/debian@$BOOKWORM_SLIM_SHA}
ARG BASE_IMAGE_SHA=${BASE_IMAGE_SHA/debian:bullseye-slim/debian@$BULLSEYE_SLIM_SHA}
# Naive way:
#
# 1. COPY . .
# 1. make neon-pg-ext
# 2. cargo build <storage binaries>
#
# But to enable docker to cache intermediate layers, we perform a few preparatory steps:
#
# - Build all postgres versions, depending on just the contents of vendor/
# - Use cargo chef to build all rust dependencies
# 1. Build all postgres versions
# Build Postgres
FROM $REPOSITORY/$IMAGE:$TAG AS pg-build
WORKDIR /home/nonroot
@@ -49,62 +16,34 @@ COPY --chown=nonroot vendor/postgres-v14 vendor/postgres-v14
COPY --chown=nonroot vendor/postgres-v15 vendor/postgres-v15
COPY --chown=nonroot vendor/postgres-v16 vendor/postgres-v16
COPY --chown=nonroot vendor/postgres-v17 vendor/postgres-v17
COPY --chown=nonroot pgxn pgxn
COPY --chown=nonroot Makefile Makefile
COPY --chown=nonroot postgres.mk postgres.mk
COPY --chown=nonroot scripts/ninstall.sh scripts/ninstall.sh
ENV BUILD_TYPE=release
RUN set -e \
&& mold -run make -j $(nproc) -s postgres
&& 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 .
# 2. Prepare cargo-chef recipe
FROM $REPOSITORY/$IMAGE:$TAG AS plan
WORKDIR /home/nonroot
COPY --chown=nonroot . .
RUN --mount=type=secret,uid=1000,id=SUBZERO_ACCESS_TOKEN \
set -e \
&& if [ -s /run/secrets/SUBZERO_ACCESS_TOKEN ]; then \
export CARGO_NET_GIT_FETCH_WITH_CLI=true && \
git config --global url."https://$(cat /run/secrets/SUBZERO_ACCESS_TOKEN)@github.com/neondatabase/subzero".insteadOf "https://github.com/neondatabase/subzero" && \
cargo add -p proxy subzero-core --git https://github.com/neondatabase/subzero --rev 396264617e78e8be428682f87469bb25429af88a; \
fi \
&& cargo chef prepare --recipe-path recipe.json
# Main build image
# Build neon binaries
FROM $REPOSITORY/$IMAGE:$TAG AS build
WORKDIR /home/nonroot
ARG GIT_VERSION=local
ARG BUILD_TAG
ARG ADDITIONAL_RUSTFLAGS=""
ENV CARGO_FEATURES="default"
ARG STABLE_PG_VERSION
# 3. Build cargo dependencies. Note that this step doesn't depend on anything else than
# `recipe.json`, so the layer can be reused as long as none of the dependencies change.
COPY --from=plan /home/nonroot/recipe.json recipe.json
RUN --mount=type=secret,uid=1000,id=SUBZERO_ACCESS_TOKEN \
set -e \
&& if [ -s /run/secrets/SUBZERO_ACCESS_TOKEN ]; then \
export CARGO_NET_GIT_FETCH_WITH_CLI=true && \
git config --global url."https://$(cat /run/secrets/SUBZERO_ACCESS_TOKEN)@github.com/neondatabase/subzero".insteadOf "https://github.com/neondatabase/subzero"; \
fi \
&& RUSTFLAGS="-Clinker=clang -Clink-arg=-fuse-ld=mold -Clink-arg=-Wl,--no-rosegment -Cforce-frame-pointers=yes ${ADDITIONAL_RUSTFLAGS}" cargo chef cook --locked --release --recipe-path recipe.json
# Perform the main build. We reuse the Postgres build artifacts from the intermediate 'pg-build'
# layer, and the cargo dependencies built in the previous step.
COPY --chown=nonroot --from=pg-build /home/nonroot/pg_install/ pg_install
COPY --from=pg-build /home/nonroot/pg_install/v14/include/postgresql/server pg_install/v14/include/postgresql/server
COPY --from=pg-build /home/nonroot/pg_install/v15/include/postgresql/server pg_install/v15/include/postgresql/server
COPY --from=pg-build /home/nonroot/pg_install/v16/include/postgresql/server pg_install/v16/include/postgresql/server
COPY --from=pg-build /home/nonroot/pg_install/v17/include/postgresql/server pg_install/v17/include/postgresql/server
COPY --from=pg-build /home/nonroot/pg_install/v16/lib pg_install/v16/lib
COPY --from=pg-build /home/nonroot/pg_install/v17/lib pg_install/v17/lib
COPY --chown=nonroot . .
COPY --chown=nonroot --from=plan /home/nonroot/proxy/Cargo.toml proxy/Cargo.toml
COPY --chown=nonroot --from=plan /home/nonroot/Cargo.lock Cargo.lock
RUN --mount=type=secret,uid=1000,id=SUBZERO_ACCESS_TOKEN \
set -e \
&& if [ -s /run/secrets/SUBZERO_ACCESS_TOKEN ]; then \
export CARGO_FEATURES="rest_broker"; \
fi \
&& RUSTFLAGS="-Clinker=clang -Clink-arg=-fuse-ld=mold -Clink-arg=-Wl,--no-rosegment -Cforce-frame-pointers=yes ${ADDITIONAL_RUSTFLAGS}" cargo build \
--features $CARGO_FEATURES \
ARG ADDITIONAL_RUSTFLAGS
RUN set -e \
&& PQ_LIB_DIR=$(pwd)/pg_install/v${STABLE_PG_VERSION}/lib RUSTFLAGS="-Clinker=clang -Clink-arg=-fuse-ld=mold -Clink-arg=-Wl,--no-rosegment ${ADDITIONAL_RUSTFLAGS}" cargo build \
--bin pg_sni_router \
--bin pageserver \
--bin pagectl \
@@ -112,38 +51,22 @@ RUN --mount=type=secret,uid=1000,id=SUBZERO_ACCESS_TOKEN \
--bin storage_broker \
--bin storage_controller \
--bin proxy \
--bin endpoint_storage \
--bin neon_local \
--bin storage_scrubber \
--locked --release \
&& mold -run make -j $(nproc) -s neon-pg-ext
--locked --release
# Assemble the final image
FROM $BASE_IMAGE_SHA
# Build final image
#
FROM debian:bullseye-slim
ARG DEFAULT_PG_VERSION
WORKDIR /data
RUN set -e \
&& echo 'Acquire::Retries "5";' > /etc/apt/apt.conf.d/80-retries \
&& apt update \
&& apt install -y \
libreadline-dev \
libseccomp-dev \
ca-certificates \
openssl \
unzip \
curl \
&& ARCH=$(uname -m) \
&& if [ "$ARCH" = "x86_64" ]; then \
curl "https://awscli.amazonaws.com/awscli-exe-linux-x86_64.zip" -o "awscliv2.zip"; \
elif [ "$ARCH" = "aarch64" ]; then \
curl "https://awscli.amazonaws.com/awscli-exe-linux-aarch64.zip" -o "awscliv2.zip"; \
else \
echo "Unsupported architecture: $ARCH" && exit 1; \
fi \
&& unzip awscliv2.zip \
&& ./aws/install \
&& rm -rf aws awscliv2.zip \
&& rm -f /etc/apt/apt.conf.d/80-retries \
&& rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* \
&& useradd -d /data neon \
&& chown -R neon:neon /data
@@ -155,18 +78,14 @@ COPY --from=build --chown=neon:neon /home/nonroot/target/release/safekeeper
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/storage_controller /usr/local/bin
COPY --from=build --chown=neon:neon /home/nonroot/target/release/proxy /usr/local/bin
COPY --from=build --chown=neon:neon /home/nonroot/target/release/endpoint_storage /usr/local/bin
COPY --from=build --chown=neon:neon /home/nonroot/target/release/neon_local /usr/local/bin
COPY --from=build --chown=neon:neon /home/nonroot/target/release/storage_scrubber /usr/local/bin
COPY --from=build /home/nonroot/pg_install/v14 /usr/local/v14/
COPY --from=build /home/nonroot/pg_install/v15 /usr/local/v15/
COPY --from=build /home/nonroot/pg_install/v16 /usr/local/v16/
COPY --from=build /home/nonroot/pg_install/v17 /usr/local/v17/
# Deprecated: Old deployment scripts use this tarball which contains all the Postgres binaries.
# That's obsolete, since all the same files are also present under /usr/local/v*. But to keep the
# old scripts working for now, create the tarball.
RUN tar -C /usr/local -cvzf /data/postgres_install.tar.gz v14 v15 v16 v17
COPY --from=pg-build /home/nonroot/pg_install/v14 /usr/local/v14/
COPY --from=pg-build /home/nonroot/pg_install/v15 /usr/local/v15/
COPY --from=pg-build /home/nonroot/pg_install/v16 /usr/local/v16/
COPY --from=pg-build /home/nonroot/pg_install/v17 /usr/local/v17/
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.
@@ -180,9 +99,15 @@ RUN mkdir -p /data/.neon/ && \
> /data/.neon/pageserver.toml && \
chown -R neon:neon /data/.neon
# When running a binary that links with libpq, default to using our most recent postgres version. Binaries
# that want a particular postgres version will select it explicitly: this is just a default.
ENV LD_LIBRARY_PATH=/usr/local/v${DEFAULT_PG_VERSION}/lib
VOLUME ["/data"]
USER neon
EXPOSE 6400
EXPOSE 9898
CMD ["/usr/local/bin/pageserver", "-D", "/data/.neon"]

229
Dockerfile.build-tools Normal file
View File

@@ -0,0 +1,229 @@
FROM debian:bullseye-slim
# Use ARG as a build-time environment variable here to allow.
# It's not supposed to be set outside.
# Alternatively it can be obtained using the following command
# ```
# . /etc/os-release && echo "${VERSION_CODENAME}"
# ```
ARG DEBIAN_VERSION_CODENAME=bullseye
# Add nonroot user
RUN useradd -ms /bin/bash nonroot -b /home
SHELL ["/bin/bash", "-c"]
# System deps
RUN set -e \
&& apt update \
&& apt install -y \
autoconf \
automake \
bison \
build-essential \
ca-certificates \
cmake \
curl \
flex \
git \
gnupg \
gzip \
jq \
libcurl4-openssl-dev \
libbz2-dev \
libffi-dev \
liblzma-dev \
libncurses5-dev \
libncursesw5-dev \
libreadline-dev \
libseccomp-dev \
libsqlite3-dev \
libssl-dev \
libstdc++-10-dev \
libtool \
libxml2-dev \
libxmlsec1-dev \
libxxhash-dev \
lsof \
make \
netcat \
net-tools \
openssh-client \
parallel \
pkg-config \
unzip \
wget \
xz-utils \
zlib1g-dev \
zstd \
&& rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
# protobuf-compiler (protoc)
ENV PROTOC_VERSION=25.1
RUN curl -fsSL "https://github.com/protocolbuffers/protobuf/releases/download/v${PROTOC_VERSION}/protoc-${PROTOC_VERSION}-linux-$(uname -m | sed 's/aarch64/aarch_64/g').zip" -o "protoc.zip" \
&& unzip -q protoc.zip -d protoc \
&& mv protoc/bin/protoc /usr/local/bin/protoc \
&& mv protoc/include/google /usr/local/include/google \
&& rm -rf protoc.zip protoc
# s5cmd
ENV S5CMD_VERSION=2.2.2
RUN curl -sL "https://github.com/peak/s5cmd/releases/download/v${S5CMD_VERSION}/s5cmd_${S5CMD_VERSION}_Linux-$(uname -m | sed 's/x86_64/64bit/g' | sed 's/aarch64/arm64/g').tar.gz" | tar zxvf - s5cmd \
&& chmod +x s5cmd \
&& mv s5cmd /usr/local/bin/s5cmd
# LLVM
ENV LLVM_VERSION=18
RUN curl -fsSL 'https://apt.llvm.org/llvm-snapshot.gpg.key' | apt-key add - \
&& echo "deb http://apt.llvm.org/${DEBIAN_VERSION_CODENAME}/ llvm-toolchain-${DEBIAN_VERSION_CODENAME}-${LLVM_VERSION} main" > /etc/apt/sources.list.d/llvm.stable.list \
&& apt update \
&& apt install -y clang-${LLVM_VERSION} llvm-${LLVM_VERSION} \
&& bash -c 'for f in /usr/bin/clang*-${LLVM_VERSION} /usr/bin/llvm*-${LLVM_VERSION}; do ln -s "${f}" "${f%-${LLVM_VERSION}}"; done' \
&& rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
# Install docker
RUN curl -fsSL https://download.docker.com/linux/ubuntu/gpg | gpg --dearmor -o /usr/share/keyrings/docker-archive-keyring.gpg \
&& echo "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/docker-archive-keyring.gpg] https://download.docker.com/linux/debian ${DEBIAN_VERSION_CODENAME} stable" > /etc/apt/sources.list.d/docker.list \
&& apt update \
&& apt install -y docker-ce docker-ce-cli \
&& rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
# Configure sudo & docker
RUN usermod -aG sudo nonroot && \
echo '%sudo ALL=(ALL) NOPASSWD:ALL' >> /etc/sudoers && \
usermod -aG docker nonroot
# AWS CLI
RUN curl "https://awscli.amazonaws.com/awscli-exe-linux-$(uname -m).zip" -o "awscliv2.zip" \
&& unzip -q awscliv2.zip \
&& ./aws/install \
&& rm awscliv2.zip
# Mold: A Modern Linker
ENV MOLD_VERSION=v2.33.0
RUN set -e \
&& git clone https://github.com/rui314/mold.git \
&& mkdir mold/build \
&& cd mold/build \
&& git checkout ${MOLD_VERSION} \
&& cmake -DCMAKE_BUILD_TYPE=Release -DCMAKE_CXX_COMPILER=clang++ .. \
&& cmake --build . -j $(nproc) \
&& cmake --install . \
&& cd .. \
&& rm -rf mold
# LCOV
# Build lcov from a fork:
# It includes several bug fixes on top on v2.0 release (https://github.com/linux-test-project/lcov/compare/v2.0...master)
# And patches from us:
# - Generates json file with code coverage summary (https://github.com/neondatabase/lcov/commit/426e7e7a22f669da54278e9b55e6d8caabd00af0.tar.gz)
RUN for package in Capture::Tiny DateTime Devel::Cover Digest::MD5 File::Spec JSON::XS Memory::Process Time::HiRes JSON; do yes | perl -MCPAN -e "CPAN::Shell->notest('install', '$package')"; done \
&& wget https://github.com/neondatabase/lcov/archive/426e7e7a22f669da54278e9b55e6d8caabd00af0.tar.gz -O lcov.tar.gz \
&& echo "61a22a62e20908b8b9e27d890bd0ea31f567a7b9668065589266371dcbca0992 lcov.tar.gz" | sha256sum --check \
&& mkdir -p lcov && tar -xzf lcov.tar.gz -C lcov --strip-components=1 \
&& cd lcov \
&& make install \
&& rm -rf ../lcov.tar.gz
# Compile and install the static OpenSSL library
ENV OPENSSL_VERSION=1.1.1w
ENV OPENSSL_PREFIX=/usr/local/openssl
RUN wget -O /tmp/openssl-${OPENSSL_VERSION}.tar.gz https://www.openssl.org/source/openssl-${OPENSSL_VERSION}.tar.gz && \
echo "cf3098950cb4d853ad95c0841f1f9c6d3dc102dccfcacd521d93925208b76ac8 /tmp/openssl-${OPENSSL_VERSION}.tar.gz" | sha256sum --check && \
cd /tmp && \
tar xzvf /tmp/openssl-${OPENSSL_VERSION}.tar.gz && \
rm /tmp/openssl-${OPENSSL_VERSION}.tar.gz && \
cd /tmp/openssl-${OPENSSL_VERSION} && \
./config --prefix=${OPENSSL_PREFIX} -static --static no-shared -fPIC && \
make -j "$(nproc)" && \
make install && \
cd /tmp && \
rm -rf /tmp/openssl-${OPENSSL_VERSION}
# Use the same version of libicu as the compute nodes so that
# clusters created using inidb on pageserver can be used by computes.
#
# TODO: at this time, Dockerfile.compute-node uses the debian bullseye libicu
# package, which is 67.1. We're duplicating that knowledge here, and also, technically,
# Debian has a few patches on top of 67.1 that we're not adding here.
ENV ICU_VERSION=67.1
ENV ICU_PREFIX=/usr/local/icu
# Download and build static ICU
RUN wget -O /tmp/libicu-${ICU_VERSION}.tgz https://github.com/unicode-org/icu/releases/download/release-${ICU_VERSION//./-}/icu4c-${ICU_VERSION//./_}-src.tgz && \
echo "94a80cd6f251a53bd2a997f6f1b5ac6653fe791dfab66e1eb0227740fb86d5dc /tmp/libicu-${ICU_VERSION}.tgz" | sha256sum --check && \
mkdir /tmp/icu && \
pushd /tmp/icu && \
tar -xzf /tmp/libicu-${ICU_VERSION}.tgz && \
pushd icu/source && \
./configure --prefix=${ICU_PREFIX} --enable-static --enable-shared=no CXXFLAGS="-fPIC" CFLAGS="-fPIC" && \
make -j "$(nproc)" && \
make install && \
popd && \
rm -rf icu && \
rm -f /tmp/libicu-${ICU_VERSION}.tgz && \
popd
# Switch to nonroot user
USER nonroot:nonroot
WORKDIR /home/nonroot
# Python
ENV PYTHON_VERSION=3.9.19 \
PYENV_ROOT=/home/nonroot/.pyenv \
PATH=/home/nonroot/.pyenv/shims:/home/nonroot/.pyenv/bin:/home/nonroot/.poetry/bin:$PATH
RUN set -e \
&& cd $HOME \
&& curl -sSO https://raw.githubusercontent.com/pyenv/pyenv-installer/master/bin/pyenv-installer \
&& chmod +x pyenv-installer \
&& ./pyenv-installer \
&& export PYENV_ROOT=/home/nonroot/.pyenv \
&& export PATH="$PYENV_ROOT/bin:$PATH" \
&& export PATH="$PYENV_ROOT/shims:$PATH" \
&& pyenv install ${PYTHON_VERSION} \
&& pyenv global ${PYTHON_VERSION} \
&& python --version \
&& pip install --upgrade pip \
&& pip --version \
&& pip install pipenv wheel poetry
# Switch to nonroot user (again)
USER nonroot:nonroot
WORKDIR /home/nonroot
# Rust
# Please keep the version of llvm (installed above) in sync with rust llvm (`rustc --version --verbose | grep LLVM`)
ENV RUSTC_VERSION=1.81.0
ENV RUSTUP_HOME="/home/nonroot/.rustup"
ENV PATH="/home/nonroot/.cargo/bin:${PATH}"
ARG RUSTFILT_VERSION=0.2.1
ARG CARGO_HAKARI_VERSION=0.9.30
ARG CARGO_DENY_VERSION=0.16.1
ARG CARGO_HACK_VERSION=0.6.31
ARG CARGO_NEXTEST_VERSION=0.9.72
RUN curl -sSO https://static.rust-lang.org/rustup/dist/$(uname -m)-unknown-linux-gnu/rustup-init && whoami && \
chmod +x rustup-init && \
./rustup-init -y --default-toolchain ${RUSTC_VERSION} && \
rm rustup-init && \
export PATH="$HOME/.cargo/bin:$PATH" && \
. "$HOME/.cargo/env" && \
cargo --version && rustup --version && \
rustup component add llvm-tools rustfmt clippy && \
cargo install rustfilt --version ${RUSTFILT_VERSION} && \
cargo install cargo-hakari --version ${CARGO_HAKARI_VERSION} && \
cargo install cargo-deny --locked --version ${CARGO_DENY_VERSION} && \
cargo install cargo-hack --version ${CARGO_HACK_VERSION} && \
cargo install cargo-nextest --version ${CARGO_NEXTEST_VERSION} && \
rm -rf /home/nonroot/.cargo/registry && \
rm -rf /home/nonroot/.cargo/git
# Show versions
RUN whoami \
&& python --version \
&& pip --version \
&& cargo --version --verbose \
&& rustup --version --verbose \
&& rustc --version --verbose \
&& clang --version
# Set following flag to check in Makefile if its running in Docker
RUN touch /home/nonroot/.docker_build

1204
Dockerfile.compute-node Normal file

File diff suppressed because it is too large Load Diff

300
Makefile
View File

@@ -1,21 +1,9 @@
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
# Supported PostgreSQL versions
POSTGRES_VERSIONS = v17 v16 v15 v14
# CARGO_BUILD_FLAGS: Extra flags to pass to `cargo build`. `--locked`
# and `--features testing` are popular examples.
#
# CARGO_PROFILE: Set to override the cargo profile to use. By default,
# it is derived from BUILD_TYPE.
# All intermediate build artifacts are stored here.
BUILD_DIR := $(ROOT_PROJECT_DIR)/build
# Where to install Postgres, default is ./pg_install, maybe useful for package managers
POSTGRES_INSTALL_DIR ?= $(ROOT_PROJECT_DIR)/pg_install/
OPENSSL_PREFIX_DIR := /usr/local/openssl
ICU_PREFIX_DIR := /usr/local/icu
#
@@ -23,53 +11,33 @@ ICU_PREFIX_DIR := /usr/local/icu
# environment variable.
#
BUILD_TYPE ?= debug
WITH_SANITIZERS ?= no
PG_CFLAGS = -fsigned-char
ifeq ($(BUILD_TYPE),release)
PG_CONFIGURE_OPTS = --enable-debug --with-openssl
PG_CFLAGS += -O2 -g3 $(CFLAGS)
PG_LDFLAGS = $(LDFLAGS)
CARGO_PROFILE ?= --profile=release
# NEON_CARGO_ARTIFACT_TARGET_DIR is the directory where `cargo build` places
# the final build artifacts. There is unfortunately no easy way of changing
# it to a fully predictable path, nor to extract the path with a simple
# command. See https://github.com/rust-lang/cargo/issues/9661 and
# https://github.com/rust-lang/cargo/issues/6790.
NEON_CARGO_ARTIFACT_TARGET_DIR = $(ROOT_PROJECT_DIR)/target/release
PG_CFLAGS = -O2 -g3 $(CFLAGS)
# Unfortunately, `--profile=...` is a nightly feature
CARGO_BUILD_FLAGS += --release
else ifeq ($(BUILD_TYPE),debug)
PG_CONFIGURE_OPTS = --enable-debug --with-openssl --enable-cassert --enable-depend
PG_CFLAGS += -O0 -g3 $(CFLAGS)
PG_LDFLAGS = $(LDFLAGS)
CARGO_PROFILE ?= --profile=dev
NEON_CARGO_ARTIFACT_TARGET_DIR = $(ROOT_PROJECT_DIR)/target/debug
PG_CFLAGS = -O0 -g3 $(CFLAGS)
else
$(error Bad build type '$(BUILD_TYPE)', see Makefile for options)
endif
ifeq ($(WITH_SANITIZERS),yes)
PG_CFLAGS += -fsanitize=address -fsanitize=undefined -fno-sanitize-recover
COPT += -Wno-error # to avoid failing on warnings induced by sanitizers
PG_LDFLAGS = -fsanitize=address -fsanitize=undefined -static-libasan -static-libubsan $(LDFLAGS)
export CC := gcc
export ASAN_OPTIONS := detect_leaks=0
endif
ifeq ($(shell test -e /home/nonroot/.docker_build && echo -n yes),yes)
# Exclude static build openssl, icu for local build (MacOS, Linux)
# Only keep for build type release and debug
PG_CFLAGS += -I$(OPENSSL_PREFIX_DIR)/include
PG_CONFIGURE_OPTS += --with-icu
PG_CONFIGURE_OPTS += ICU_CFLAGS='-I/$(ICU_PREFIX_DIR)/include -DU_STATIC_IMPLEMENTATION'
PG_CONFIGURE_OPTS += ICU_LIBS='-L$(ICU_PREFIX_DIR)/lib -L$(ICU_PREFIX_DIR)/lib64 -licui18n -licuuc -licudata -lstdc++ -Wl,-Bdynamic -lm'
PG_CONFIGURE_OPTS += LDFLAGS='-L$(OPENSSL_PREFIX_DIR)/lib -L$(OPENSSL_PREFIX_DIR)/lib64 -L$(ICU_PREFIX_DIR)/lib -L$(ICU_PREFIX_DIR)/lib64 -Wl,-Bstatic -lssl -lcrypto -Wl,-Bdynamic -lrt -lm -ldl -lpthread'
endif
UNAME_S := $(shell uname -s)
ifeq ($(UNAME_S),Linux)
# Seccomp BPF is only available for Linux
ifneq ($(WITH_SANITIZERS),yes)
PG_CONFIGURE_OPTS += --with-libseccomp
endif
PG_CONFIGURE_OPTS += --with-libseccomp
else ifeq ($(UNAME_S),Darwin)
PG_CFLAGS += -DUSE_PREFETCH
ifndef DISABLE_HOMEBREW
# macOS with brew-installed openssl requires explicit paths
# It can be configured with OPENSSL_PREFIX variable
@@ -98,6 +66,8 @@ CARGO_BUILD_FLAGS += $(filter -j1,$(MAKEFLAGS))
CARGO_CMD_PREFIX += $(if $(filter n,$(MAKEFLAGS)),,+)
# Force cargo not to print progress bar
CARGO_CMD_PREFIX += CARGO_TERM_PROGRESS_WHEN=never CI=1
# Set PQ_LIB_DIR to make sure `storage_controller` get linked with bundled libpq (through diesel)
CARGO_CMD_PREFIX += PQ_LIB_DIR=$(POSTGRES_INSTALL_DIR)/v16/lib
CACHEDIR_TAG_CONTENTS := "Signature: 8a477f597d28d172789f06886806bc55"
@@ -105,32 +75,137 @@ CACHEDIR_TAG_CONTENTS := "Signature: 8a477f597d28d172789f06886806bc55"
# Top level Makefile to build Neon and PostgreSQL
#
.PHONY: all
all: neon postgres-install neon-pg-ext
all: neon postgres neon-pg-ext
### Neon Rust bits
#
# The 'postgres_ffi' crate depends on the Postgres headers.
# The 'postgres_ffi' depends on the Postgres headers.
.PHONY: neon
neon: postgres-headers-install walproposer-lib cargo-target-dir
neon: postgres-headers walproposer-lib cargo-target-dir
+@echo "Compiling Neon"
$(CARGO_CMD_PREFIX) cargo build $(CARGO_BUILD_FLAGS) $(CARGO_PROFILE)
$(CARGO_CMD_PREFIX) cargo build $(CARGO_BUILD_FLAGS)
.PHONY: cargo-target-dir
cargo-target-dir:
# https://github.com/rust-lang/cargo/issues/14281
mkdir -p target
test -e target/CACHEDIR.TAG || echo "$(CACHEDIR_TAG_CONTENTS)" > target/CACHEDIR.TAG
### 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:
mkdir -p $(POSTGRES_INSTALL_DIR)
test -e $(POSTGRES_INSTALL_DIR)/CACHEDIR.TAG || echo "$(CACHEDIR_TAG_CONTENTS)" > $(POSTGRES_INSTALL_DIR)/CACHEDIR.TAG
+@echo "Configuring Postgres $* build"
@test -s $(ROOT_PROJECT_DIR)/vendor/postgres-$*/configure || { \
echo "\nPostgres submodule not found in $(ROOT_PROJECT_DIR)/vendor/postgres-$*/, execute "; \
echo "'git submodule update --init --recursive --depth 2 --progress .' in project root.\n"; \
exit 1; }
mkdir -p $(POSTGRES_INSTALL_DIR)/build/$*
VERSION=$*; \
EXTRA_VERSION=$$(cd $(ROOT_PROJECT_DIR)/vendor/postgres-$$VERSION && git rev-parse HEAD); \
(cd $(POSTGRES_INSTALL_DIR)/build/$$VERSION && \
env PATH="$(EXTRA_PATH_OVERRIDES):$$PATH" $(ROOT_PROJECT_DIR)/vendor/postgres-$$VERSION/configure \
CFLAGS='$(PG_CFLAGS)' \
$(PG_CONFIGURE_OPTS) --with-extra-version=" ($$EXTRA_VERSION)" \
--prefix=$(abspath $(POSTGRES_INSTALL_DIR))/$$VERSION > 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-v17
postgres-configure-v17: $(POSTGRES_INSTALL_DIR)/build/v17/config.status
.PHONY: postgres-configure-v16
postgres-configure-v16: $(POSTGRES_INSTALL_DIR)/build/v16/config.status
.PHONY: postgres-configure-v15
postgres-configure-v15: $(POSTGRES_INSTALL_DIR)/build/v15/config.status
.PHONY: postgres-configure-v14
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
+@echo "Compiling amcheck $*"
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/amcheck install
+@echo "Compiling test_decoding $*"
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/test_decoding install
.PHONY: postgres-clean-%
postgres-clean-%:
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$* MAKELEVEL=0 clean
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pg_buffercache clean
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/contrib/pageinspect clean
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/src/interfaces/libpq clean
.PHONY: postgres-check-%
postgres-check-%: postgres-%
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$* MAKELEVEL=0 check
.PHONY: neon-pg-ext-%
neon-pg-ext-%: postgres-install-% cargo-target-dir
+@echo "Compiling neon-specific Postgres extensions for $*"
mkdir -p $(BUILD_DIR)/pgxn-$*
$(MAKE) PG_CONFIG="$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config" COPT='$(COPT)' \
NEON_CARGO_ARTIFACT_TARGET_DIR="$(NEON_CARGO_ARTIFACT_TARGET_DIR)" \
CARGO_BUILD_FLAGS="$(CARGO_BUILD_FLAGS)" \
CARGO_PROFILE="$(CARGO_PROFILE)" \
-C $(BUILD_DIR)/pgxn-$*\
-f $(ROOT_PROJECT_DIR)/pgxn/Makefile install
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_rmgr $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-rmgr-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-rmgr-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_rmgr/Makefile install
+@echo "Compiling neon_test_utils $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_test_utils/Makefile install
+@echo "Compiling neon_utils $*"
mkdir -p $(POSTGRES_INSTALL_DIR)/build/neon-utils-$*
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/neon-utils-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_utils/Makefile install
.PHONY: neon-pg-clean-ext-%
neon-pg-clean-ext-%:
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config \
-C $(POSTGRES_INSTALL_DIR)/build/neon-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile clean
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config \
-C $(POSTGRES_INSTALL_DIR)/build/neon-walredo-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_walredo/Makefile clean
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config \
-C $(POSTGRES_INSTALL_DIR)/build/neon-test-utils-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_test_utils/Makefile clean
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/$*/bin/pg_config \
-C $(POSTGRES_INSTALL_DIR)/build/neon-utils-$* \
-f $(ROOT_PROJECT_DIR)/pgxn/neon_utils/Makefile clean
# Build walproposer as a static library. walproposer source code is located
# in the pgxn/neon directory.
@@ -144,15 +219,15 @@ neon-pg-ext-%: postgres-install-% cargo-target-dir
.PHONY: walproposer-lib
walproposer-lib: neon-pg-ext-v17
+@echo "Compiling walproposer-lib"
mkdir -p $(BUILD_DIR)/walproposer-lib
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v17/bin/pg_config COPT='$(COPT)' \
-C $(BUILD_DIR)/walproposer-lib \
mkdir -p $(POSTGRES_INSTALL_DIR)/build/walproposer-lib
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v17/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
-C $(POSTGRES_INSTALL_DIR)/build/walproposer-lib \
-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile walproposer-lib
cp $(POSTGRES_INSTALL_DIR)/v17/lib/libpgport.a $(BUILD_DIR)/walproposer-lib
cp $(POSTGRES_INSTALL_DIR)/v17/lib/libpgcommon.a $(BUILD_DIR)/walproposer-lib
$(AR) d $(BUILD_DIR)/walproposer-lib/libpgport.a \
cp $(POSTGRES_INSTALL_DIR)/v17/lib/libpgport.a $(POSTGRES_INSTALL_DIR)/build/walproposer-lib
cp $(POSTGRES_INSTALL_DIR)/v17/lib/libpgcommon.a $(POSTGRES_INSTALL_DIR)/build/walproposer-lib
$(AR) d $(POSTGRES_INSTALL_DIR)/build/walproposer-lib/libpgport.a \
pg_strong_random.o
$(AR) d $(BUILD_DIR)/walproposer-lib/libpgcommon.a \
$(AR) d $(POSTGRES_INSTALL_DIR)/build/walproposer-lib/libpgcommon.a \
checksum_helper.o \
cryptohash_openssl.o \
hmac_openssl.o \
@@ -160,18 +235,68 @@ walproposer-lib: neon-pg-ext-v17
parse_manifest.o \
scram-common.o
ifeq ($(UNAME_S),Linux)
$(AR) d $(BUILD_DIR)/walproposer-lib/libpgcommon.a \
$(AR) d $(POSTGRES_INSTALL_DIR)/build/walproposer-lib/libpgcommon.a \
pg_crc32c.o
endif
# Shorthand to call neon-pg-ext-% target for all Postgres versions
.PHONY: walproposer-lib-clean
walproposer-lib-clean:
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v17/bin/pg_config \
-C $(POSTGRES_INSTALL_DIR)/build/walproposer-lib \
-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile clean
.PHONY: neon-pg-ext
neon-pg-ext: $(foreach pg_version,$(POSTGRES_VERSIONS),neon-pg-ext-$(pg_version))
neon-pg-ext: \
neon-pg-ext-v14 \
neon-pg-ext-v15 \
neon-pg-ext-v16 \
neon-pg-ext-v17
.PHONY: neon-pg-clean-ext
neon-pg-clean-ext: \
neon-pg-clean-ext-v14 \
neon-pg-clean-ext-v15 \
neon-pg-clean-ext-v16 \
neon-pg-clean-ext-v17
# shorthand to build all Postgres versions
.PHONY: postgres
postgres: \
postgres-v14 \
postgres-v15 \
postgres-v16 \
postgres-v17
.PHONY: postgres-headers
postgres-headers: \
postgres-headers-v14 \
postgres-headers-v15 \
postgres-headers-v16 \
postgres-headers-v17
.PHONY: postgres-clean
postgres-clean: \
postgres-clean-v14 \
postgres-clean-v15 \
postgres-clean-v16 \
postgres-clean-v17
.PHONY: postgres-check
postgres-check: \
postgres-check-v14 \
postgres-check-v15 \
postgres-check-v16 \
postgres-check-v17
# This doesn't remove the effects of 'configure'.
.PHONY: clean
clean: postgres-clean neon-pg-clean-ext
$(CARGO_CMD_PREFIX) cargo clean
# This removes everything
.PHONY: distclean
distclean:
$(RM) -r $(POSTGRES_INSTALL_DIR) $(BUILD_DIR)
rm -rf $(POSTGRES_INSTALL_DIR)
$(CARGO_CMD_PREFIX) cargo clean
.PHONY: fmt
@@ -180,7 +305,7 @@ fmt:
postgres-%-pg-bsd-indent: postgres-%
+@echo "Compiling pg_bsd_indent"
$(MAKE) -C $(BUILD_DIR)/$*/src/tools/pg_bsd_indent/
$(MAKE) -C $(POSTGRES_INSTALL_DIR)/build/$*/src/tools/pg_bsd_indent/
# Create typedef list for the core. Note that generally it should be combined with
# buildfarm one to cover platform specific stuff.
@@ -199,52 +324,23 @@ postgres-%-pgindent: postgres-%-pg-bsd-indent postgres-%-typedefs.list
cat $(ROOT_PROJECT_DIR)/vendor/postgres-$*/src/tools/pgindent/typedefs.list |\
cat - postgres-$*-typedefs.list | sort | uniq > postgres-$*-typedefs-full.list
+@echo note: you might want to run it on selected files/dirs instead.
INDENT=$(BUILD_DIR)/$*/src/tools/pg_bsd_indent/pg_bsd_indent \
INDENT=$(POSTGRES_INSTALL_DIR)/build/$*/src/tools/pg_bsd_indent/pg_bsd_indent \
$(ROOT_PROJECT_DIR)/vendor/postgres-$*/src/tools/pgindent/pgindent --typedefs postgres-$*-typedefs-full.list \
$(ROOT_PROJECT_DIR)/vendor/postgres-$*/src/ \
--excludes $(ROOT_PROJECT_DIR)/vendor/postgres-$*/src/tools/pgindent/exclude_file_patterns
$(RM) pg*.BAK
rm -f pg*.BAK
# Indent pxgn/neon.
.PHONY: neon-pgindent
neon-pgindent: postgres-v17-pg-bsd-indent neon-pg-ext-v17
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v17/bin/pg_config COPT='$(COPT)' \
$(MAKE) PG_CONFIG=$(POSTGRES_INSTALL_DIR)/v17/bin/pg_config CFLAGS='$(PG_CFLAGS) $(COPT)' \
FIND_TYPEDEF=$(ROOT_PROJECT_DIR)/vendor/postgres-v17/src/tools/find_typedef \
INDENT=$(BUILD_DIR)/v17/src/tools/pg_bsd_indent/pg_bsd_indent \
INDENT=$(POSTGRES_INSTALL_DIR)/build/v17/src/tools/pg_bsd_indent/pg_bsd_indent \
PGINDENT_SCRIPT=$(ROOT_PROJECT_DIR)/vendor/postgres-v17/src/tools/pgindent/pgindent \
-C $(BUILD_DIR)/pgxn-v17/neon \
-C $(POSTGRES_INSTALL_DIR)/build/neon-v17 \
-f $(ROOT_PROJECT_DIR)/pgxn/neon/Makefile pgindent
.PHONY: setup-pre-commit-hook
setup-pre-commit-hook:
ln -s -f $(ROOT_PROJECT_DIR)/pre-commit.py .git/hooks/pre-commit
build-tools/node_modules: build-tools/package.json
cd build-tools && $(if $(CI),npm ci,npm install)
touch build-tools/node_modules
.PHONY: lint-openapi-spec
lint-openapi-spec: build-tools/node_modules
# operation-2xx-response: pageserver timeline delete returns 404 on success
find . -iname "openapi_spec.y*ml" -exec\
npx --prefix=build-tools/ redocly\
--skip-rule=operation-operationId --skip-rule=operation-summary --extends=minimal\
--skip-rule=no-server-example.com --skip-rule=operation-2xx-response\
lint {} \+
# Targets for building PostgreSQL are defined in postgres.mk.
#
# But if the caller has indicated that PostgreSQL is already
# installed, by setting the PG_INSTALL_CACHED variable, skip it.
ifdef PG_INSTALL_CACHED
postgres-install: skip-install
$(foreach pg_version,$(POSTGRES_VERSIONS),postgres-install-$(pg_version)): skip-install
postgres-headers-install:
+@echo "Skipping installation of PostgreSQL headers because PG_INSTALL_CACHED is set"
skip-install:
+@echo "Skipping PostgreSQL installation because PG_INSTALL_CACHED is set"
else
include postgres.mk
endif

View File

@@ -21,10 +21,8 @@ The Neon storage engine consists of two major components:
See developer documentation in [SUMMARY.md](/docs/SUMMARY.md) for more information.
## Running a local development environment
## Running local installation
Neon can be run on a workstation for small experiments and to test code changes, by
following these instructions.
#### Installing dependencies on Linux
1. Install build dependencies and other applicable packages
@@ -33,7 +31,7 @@ following these instructions.
```bash
apt install build-essential libtool libreadline-dev zlib1g-dev flex bison libseccomp-dev \
libssl-dev clang pkg-config libpq-dev cmake postgresql-client protobuf-compiler \
libprotobuf-dev libcurl4-openssl-dev openssl python3-poetry lsof libicu-dev
libcurl4-openssl-dev openssl python3-poetry lsof libicu-dev
```
* On Fedora, these packages are needed:
```bash
@@ -60,7 +58,7 @@ curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
1. Install XCode and dependencies
```
xcode-select --install
brew install protobuf openssl flex bison icu4c pkg-config m4
brew install protobuf openssl flex bison icu4c pkg-config
# add openssl to PATH, required for ed25519 keys generation in neon_local
echo 'export PATH="$(brew --prefix openssl)/bin:$PATH"' >> ~/.zshrc
@@ -134,7 +132,7 @@ make -j`sysctl -n hw.logicalcpu` -s
To run the `psql` client, install the `postgresql-client` package or modify `PATH` and `LD_LIBRARY_PATH` to include `pg_install/bin` and `pg_install/lib`, respectively.
To run the integration tests or Python scripts (not required to use the code), install
Python (3.11 or higher), and install the python3 packages using `./scripts/pysync` (requires [poetry>=1.8](https://python-poetry.org/)) in the project directory.
Python (3.9 or higher), and install the python3 packages using `./scripts/pysync` (requires [poetry>=1.8](https://python-poetry.org/)) in the project directory.
#### Running neon database
@@ -240,7 +238,7 @@ postgres=# select * from t;
> cargo neon stop
```
More advanced usages can be found at [Local Development Control Plane (`neon_local`))](./control_plane/README.md).
More advanced usages can be found at [Control Plane and Neon Local](./control_plane/README.md).
#### Handling build failures
@@ -270,7 +268,7 @@ By default, this runs both debug and release modes, and all supported postgres v
testing locally, it is convenient to run just one set of permutations, like this:
```sh
DEFAULT_PG_VERSION=17 BUILD_TYPE=release ./scripts/pytest
DEFAULT_PG_VERSION=16 BUILD_TYPE=release ./scripts/pytest
```
## Flamegraphs

View File

@@ -1,347 +0,0 @@
ARG DEBIAN_VERSION=bookworm
ARG DEBIAN_FLAVOR=${DEBIAN_VERSION}-slim
# Here are the INDEX DIGESTS for the images we use.
# You can get them following next steps for now:
# 1. Get an authentication token from DockerHub:
# TOKEN=$(curl -s "https://auth.docker.io/token?service=registry.docker.io&scope=repository:library/debian:pull" | jq -r .token)
# 2. Using that token, query index for the given tag:
# curl -s -H "Authorization: Bearer $TOKEN" \
# -H "Accept: application/vnd.docker.distribution.manifest.list.v2+json" \
# "https://registry.hub.docker.com/v2/library/debian/manifests/bullseye-slim" \
# -I | grep -i docker-content-digest
# 3. As a next step, TODO(fedordikarev): create script and schedule workflow to run these checks
# and updates on regular bases and in automated way.
ARG BOOKWORM_SLIM_SHA=sha256:40b107342c492725bc7aacbe93a49945445191ae364184a6d24fedb28172f6f7
ARG BULLSEYE_SLIM_SHA=sha256:e831d9a884d63734fe3dd9c491ed9a5a3d4c6a6d32c5b14f2067357c49b0b7e1
# Here we use ${var/search/replace} syntax, to check
# if base image is one of the images, we pin image index for.
# If var will match one the known images, we will replace it with the known sha.
# If no match, than value will be unaffected, and will process with no-pinned image.
ARG BASE_IMAGE_SHA=debian:${DEBIAN_FLAVOR}
ARG BASE_IMAGE_SHA=${BASE_IMAGE_SHA/debian:bookworm-slim/debian@$BOOKWORM_SLIM_SHA}
ARG BASE_IMAGE_SHA=${BASE_IMAGE_SHA/debian:bullseye-slim/debian@$BULLSEYE_SLIM_SHA}
FROM $BASE_IMAGE_SHA AS pgcopydb_builder
ARG DEBIAN_VERSION
# Use strict mode for bash to catch errors early
SHELL ["/bin/bash", "-euo", "pipefail", "-c"]
# By default, /bin/sh used in debian images will treat '\n' as eol,
# but as we use bash as SHELL, and built-in echo in bash requires '-e' flag for that.
RUN echo 'Acquire::Retries "5";' > /etc/apt/apt.conf.d/80-retries && \
echo -e "retry_connrefused=on\ntimeout=15\ntries=5\nretry-on-host-error=on\n" > /root/.wgetrc && \
echo -e "--retry-connrefused\n--connect-timeout 15\n--retry 5\n--max-time 300\n" > /root/.curlrc
COPY build-tools/patches/pgcopydbv017.patch /pgcopydbv017.patch
RUN if [ "${DEBIAN_VERSION}" = "bookworm" ]; then \
set -e && \
apt update && \
apt install -y --no-install-recommends \
ca-certificates wget gpg && \
wget -qO - https://www.postgresql.org/media/keys/ACCC4CF8.asc | gpg --dearmor -o /usr/share/keyrings/postgresql-keyring.gpg && \
echo "deb [signed-by=/usr/share/keyrings/postgresql-keyring.gpg] http://apt.postgresql.org/pub/repos/apt bookworm-pgdg main" > /etc/apt/sources.list.d/pgdg.list && \
apt-get update && \
apt install -y --no-install-recommends \
build-essential \
autotools-dev \
libedit-dev \
libgc-dev \
libpam0g-dev \
libreadline-dev \
libselinux1-dev \
libxslt1-dev \
libssl-dev \
libkrb5-dev \
zlib1g-dev \
liblz4-dev \
libpq5 \
libpq-dev \
libzstd-dev \
postgresql-16 \
postgresql-server-dev-16 \
postgresql-common \
python3-sphinx && \
wget -O /tmp/pgcopydb.tar.gz https://github.com/dimitri/pgcopydb/archive/refs/tags/v0.17.tar.gz && \
mkdir /tmp/pgcopydb && \
tar -xzf /tmp/pgcopydb.tar.gz -C /tmp/pgcopydb --strip-components=1 && \
cd /tmp/pgcopydb && \
patch -p1 < /pgcopydbv017.patch && \
make -s clean && \
make -s -j12 install && \
libpq_path=$(find /lib /usr/lib -name "libpq.so.5" | head -n 1) && \
mkdir -p /pgcopydb/lib && \
cp "$libpq_path" /pgcopydb/lib/; \
else \
# copy command below will fail if we don't have dummy files, so we create them for other debian versions
mkdir -p /usr/lib/postgresql/16/bin && touch /usr/lib/postgresql/16/bin/pgcopydb && \
mkdir -p mkdir -p /pgcopydb/lib && touch /pgcopydb/lib/libpq.so.5; \
fi
FROM $BASE_IMAGE_SHA AS build_tools
ARG DEBIAN_VERSION
# Add nonroot user
RUN useradd -ms /bin/bash nonroot -b /home
# Use strict mode for bash to catch errors early
SHELL ["/bin/bash", "-euo", "pipefail", "-c"]
RUN mkdir -p /pgcopydb/bin && \
mkdir -p /pgcopydb/lib && \
chmod -R 755 /pgcopydb && \
chown -R nonroot:nonroot /pgcopydb
COPY --from=pgcopydb_builder /usr/lib/postgresql/16/bin/pgcopydb /pgcopydb/bin/pgcopydb
COPY --from=pgcopydb_builder /pgcopydb/lib/libpq.so.5 /pgcopydb/lib/libpq.so.5
RUN echo 'Acquire::Retries "5";' > /etc/apt/apt.conf.d/80-retries && \
echo -e "retry_connrefused=on\ntimeout=15\ntries=5\nretry-on-host-error=on\n" > /root/.wgetrc && \
echo -e "--retry-connrefused\n--connect-timeout 15\n--retry 5\n--max-time 300\n" > /root/.curlrc
# System deps
#
# 'gdb' is included so that we get backtraces of core dumps produced in
# regression tests
RUN set -e \
&& apt update \
&& apt install -y \
autoconf \
automake \
bison \
build-essential \
ca-certificates \
cmake \
curl \
flex \
gdb \
git \
gnupg \
gzip \
jq \
jsonnet \
libcurl4-openssl-dev \
libbz2-dev \
libffi-dev \
liblzma-dev \
libncurses5-dev \
libncursesw5-dev \
libreadline-dev \
libseccomp-dev \
libsqlite3-dev \
libssl-dev \
$([[ "${DEBIAN_VERSION}" = "bullseye" ]] && echo libstdc++-10-dev || echo libstdc++-11-dev) \
libtool \
libxml2-dev \
libxmlsec1-dev \
libxxhash-dev \
lsof \
make \
netcat-openbsd \
net-tools \
openssh-client \
parallel \
pkg-config \
unzip \
wget \
xz-utils \
zlib1g-dev \
zstd \
&& rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
# sql_exporter
# Keep the version the same as in compute/compute-node.Dockerfile and
# test_runner/regress/test_compute_metrics.py.
ENV SQL_EXPORTER_VERSION=0.17.3
RUN curl -fsSL \
"https://github.com/burningalchemist/sql_exporter/releases/download/${SQL_EXPORTER_VERSION}/sql_exporter-${SQL_EXPORTER_VERSION}.linux-$(case "$(uname -m)" in x86_64) echo amd64;; aarch64) echo arm64;; esac).tar.gz" \
--output sql_exporter.tar.gz \
&& mkdir /tmp/sql_exporter \
&& tar xzvf sql_exporter.tar.gz -C /tmp/sql_exporter --strip-components=1 \
&& mv /tmp/sql_exporter/sql_exporter /usr/local/bin/sql_exporter \
&& rm sql_exporter.tar.gz
# protobuf-compiler (protoc)
# Keep the version the same as in compute/compute-node.Dockerfile
ENV PROTOC_VERSION=25.1
RUN curl -fsSL "https://github.com/protocolbuffers/protobuf/releases/download/v${PROTOC_VERSION}/protoc-${PROTOC_VERSION}-linux-$(uname -m | sed 's/aarch64/aarch_64/g').zip" -o "protoc.zip" \
&& unzip -q protoc.zip -d protoc \
&& mv protoc/bin/protoc /usr/local/bin/protoc \
&& mv protoc/include/google /usr/local/include/google \
&& rm -rf protoc.zip protoc
# s5cmd
ENV S5CMD_VERSION=2.3.0
RUN curl -sL "https://github.com/peak/s5cmd/releases/download/v${S5CMD_VERSION}/s5cmd_${S5CMD_VERSION}_Linux-$(uname -m | sed 's/x86_64/64bit/g' | sed 's/aarch64/arm64/g').tar.gz" | tar zxvf - s5cmd \
&& chmod +x s5cmd \
&& mv s5cmd /usr/local/bin/s5cmd
# LLVM
ENV LLVM_VERSION=20
RUN curl -fsSL 'https://apt.llvm.org/llvm-snapshot.gpg.key' | apt-key add - \
&& echo "deb http://apt.llvm.org/${DEBIAN_VERSION}/ llvm-toolchain-${DEBIAN_VERSION}-${LLVM_VERSION} main" > /etc/apt/sources.list.d/llvm.stable.list \
&& apt update \
&& apt install -y clang-${LLVM_VERSION} llvm-${LLVM_VERSION} \
&& bash -c 'for f in /usr/bin/clang*-${LLVM_VERSION} /usr/bin/llvm*-${LLVM_VERSION}; do ln -s "${f}" "${f%-${LLVM_VERSION}}"; done' \
&& rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
# Install node
ENV NODE_VERSION=24
RUN curl -fsSL https://deb.nodesource.com/setup_${NODE_VERSION}.x | bash - \
&& apt install -y nodejs \
&& rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
# Install docker
RUN curl -fsSL https://download.docker.com/linux/ubuntu/gpg | gpg --dearmor -o /usr/share/keyrings/docker-archive-keyring.gpg \
&& echo "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/docker-archive-keyring.gpg] https://download.docker.com/linux/debian ${DEBIAN_VERSION} stable" > /etc/apt/sources.list.d/docker.list \
&& apt update \
&& apt install -y docker-ce docker-ce-cli \
&& rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
# Configure sudo & docker
RUN usermod -aG sudo nonroot && \
echo '%sudo ALL=(ALL) NOPASSWD:ALL' >> /etc/sudoers && \
usermod -aG docker nonroot
# AWS CLI
RUN curl "https://awscli.amazonaws.com/awscli-exe-linux-$(uname -m).zip" -o "awscliv2.zip" \
&& unzip -q awscliv2.zip \
&& ./aws/install \
&& rm awscliv2.zip
# Mold: A Modern Linker
ENV MOLD_VERSION=v2.37.1
RUN set -e \
&& git clone https://github.com/rui314/mold.git \
&& mkdir mold/build \
&& cd mold/build \
&& git checkout ${MOLD_VERSION} \
&& cmake -DCMAKE_BUILD_TYPE=Release -DCMAKE_CXX_COMPILER=clang++ .. \
&& cmake --build . -j $(nproc) \
&& cmake --install . \
&& cd .. \
&& rm -rf mold
# LCOV
# Build lcov from a fork:
# It includes several bug fixes on top on v2.0 release (https://github.com/linux-test-project/lcov/compare/v2.0...master)
# And patches from us:
# - Generates json file with code coverage summary (https://github.com/neondatabase/lcov/commit/426e7e7a22f669da54278e9b55e6d8caabd00af0.tar.gz)
RUN set +o pipefail && \
for package in Capture::Tiny DateTime Devel::Cover Digest::MD5 File::Spec JSON::XS Memory::Process Time::HiRes JSON; do \
yes | perl -MCPAN -e "CPAN::Shell->notest('install', '$package')";\
done && \
set -o pipefail
# Split into separate step to debug flaky failures here
RUN wget https://github.com/neondatabase/lcov/archive/426e7e7a22f669da54278e9b55e6d8caabd00af0.tar.gz -O lcov.tar.gz \
&& ls -laht lcov.tar.gz && sha256sum lcov.tar.gz \
&& echo "61a22a62e20908b8b9e27d890bd0ea31f567a7b9668065589266371dcbca0992 lcov.tar.gz" | sha256sum --check \
&& mkdir -p lcov && tar -xzf lcov.tar.gz -C lcov --strip-components=1 \
&& cd lcov \
&& make install \
&& rm -rf ../lcov.tar.gz
# Use the same version of libicu as the compute nodes so that
# clusters created using inidb on pageserver can be used by computes.
#
# TODO: at this time, compute-node.Dockerfile uses the debian bullseye libicu
# package, which is 67.1. We're duplicating that knowledge here, and also, technically,
# Debian has a few patches on top of 67.1 that we're not adding here.
ENV ICU_VERSION=67.1
ENV ICU_PREFIX=/usr/local/icu
# Download and build static ICU
RUN wget -O /tmp/libicu-${ICU_VERSION}.tgz https://github.com/unicode-org/icu/releases/download/release-${ICU_VERSION//./-}/icu4c-${ICU_VERSION//./_}-src.tgz && \
echo "94a80cd6f251a53bd2a997f6f1b5ac6653fe791dfab66e1eb0227740fb86d5dc /tmp/libicu-${ICU_VERSION}.tgz" | sha256sum --check && \
mkdir /tmp/icu && \
pushd /tmp/icu && \
tar -xzf /tmp/libicu-${ICU_VERSION}.tgz && \
pushd icu/source && \
./configure --prefix=${ICU_PREFIX} --enable-static --enable-shared=no CXXFLAGS="-fPIC" CFLAGS="-fPIC" && \
make -j "$(nproc)" && \
make install && \
popd && \
rm -rf icu && \
rm -f /tmp/libicu-${ICU_VERSION}.tgz && \
popd
# Switch to nonroot user
USER nonroot:nonroot
WORKDIR /home/nonroot
RUN echo -e "--retry-connrefused\n--connect-timeout 15\n--retry 5\n--max-time 300\n" > /home/nonroot/.curlrc
# Python
ENV PYTHON_VERSION=3.11.12 \
PYENV_ROOT=/home/nonroot/.pyenv \
PATH=/home/nonroot/.pyenv/shims:/home/nonroot/.pyenv/bin:/home/nonroot/.poetry/bin:$PATH
RUN set -e \
&& cd $HOME \
&& curl -sSO https://raw.githubusercontent.com/pyenv/pyenv-installer/master/bin/pyenv-installer \
&& chmod +x pyenv-installer \
&& ./pyenv-installer \
&& export PYENV_ROOT=/home/nonroot/.pyenv \
&& export PATH="$PYENV_ROOT/bin:$PATH" \
&& export PATH="$PYENV_ROOT/shims:$PATH" \
&& pyenv install ${PYTHON_VERSION} \
&& pyenv global ${PYTHON_VERSION} \
&& python --version \
&& pip install --upgrade pip \
&& pip --version \
&& pip install pipenv wheel poetry
# Switch to nonroot user (again)
USER nonroot:nonroot
WORKDIR /home/nonroot
# Rust
# Please keep the version of llvm (installed above) in sync with rust llvm (`rustc --version --verbose | grep LLVM`)
ENV RUSTC_VERSION=1.88.0
ENV RUSTUP_HOME="/home/nonroot/.rustup"
ENV PATH="/home/nonroot/.cargo/bin:${PATH}"
ARG RUSTFILT_VERSION=0.2.1
ARG CARGO_HAKARI_VERSION=0.9.36
ARG CARGO_DENY_VERSION=0.18.2
ARG CARGO_HACK_VERSION=0.6.36
ARG CARGO_NEXTEST_VERSION=0.9.94
ARG CARGO_CHEF_VERSION=0.1.71
ARG CARGO_DIESEL_CLI_VERSION=2.2.9
RUN curl -sSO https://static.rust-lang.org/rustup/dist/$(uname -m)-unknown-linux-gnu/rustup-init && whoami && \
chmod +x rustup-init && \
./rustup-init -y --default-toolchain ${RUSTC_VERSION} && \
rm rustup-init && \
export PATH="$HOME/.cargo/bin:$PATH" && \
. "$HOME/.cargo/env" && \
cargo --version && rustup --version && \
rustup component add llvm-tools rustfmt clippy && \
cargo install rustfilt --locked --version ${RUSTFILT_VERSION} && \
cargo install cargo-hakari --locked --version ${CARGO_HAKARI_VERSION} && \
cargo install cargo-deny --locked --version ${CARGO_DENY_VERSION} && \
cargo install cargo-hack --locked --version ${CARGO_HACK_VERSION} && \
cargo install cargo-nextest --locked --version ${CARGO_NEXTEST_VERSION} && \
cargo install cargo-chef --locked --version ${CARGO_CHEF_VERSION} && \
cargo install diesel_cli --locked --version ${CARGO_DIESEL_CLI_VERSION} \
--features postgres-bundled --no-default-features && \
rm -rf /home/nonroot/.cargo/registry && \
rm -rf /home/nonroot/.cargo/git
# Show versions
RUN whoami \
&& python --version \
&& pip --version \
&& cargo --version --verbose \
&& rustup --version --verbose \
&& rustc --version --verbose \
&& clang --version
RUN if [ "${DEBIAN_VERSION}" = "bookworm" ]; then \
LD_LIBRARY_PATH=/pgcopydb/lib /pgcopydb/bin/pgcopydb --version; \
else \
echo "pgcopydb is not available for ${DEBIAN_VERSION}"; \
fi
# Set following flag to check in Makefile if its running in Docker
RUN touch /home/nonroot/.docker_build

File diff suppressed because it is too large Load Diff

View File

@@ -1,8 +0,0 @@
{
"name": "build-tools",
"private": true,
"devDependencies": {
"@redocly/cli": "1.34.5",
"@sourcemeta/jsonschema": "10.0.0"
}
}

View File

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

View File

@@ -1,12 +1,9 @@
disallowed-methods = [
"tokio::task::block_in_place",
# Allow this for now, to deny it later once we stop using Handle::block_on completely
# "tokio::runtime::Handle::block_on",
# tokio-epoll-uring:
# - allow-invalid because the method doesn't exist on macOS
{ path = "tokio_epoll_uring::thread_local_system", replacement = "tokio_epoll_uring_ext module inside pageserver crate", allow-invalid = true }
# use tokio_epoll_uring_ext instead
"tokio_epoll_uring::thread_local_system",
]
disallowed-macros = [
@@ -15,5 +12,3 @@ disallowed-macros = [
# cannot disallow this, because clippy finds used from tokio macros
#"tokio::pin",
]
allow-unwrap-in-tests = true

8
compute/.gitignore vendored
View File

@@ -1,8 +0,0 @@
# sql_exporter config files generated from Jsonnet
etc/neon_collector.yml
etc/neon_collector_autoscaling.yml
etc/sql_exporter.yml
etc/sql_exporter_autoscaling.yml
# Node.js dependencies
node_modules/

View File

@@ -1,58 +0,0 @@
jsonnet_files = $(wildcard \
etc/*.jsonnet \
etc/sql_exporter/*.libsonnet)
.PHONY: all
all: neon_collector.yml neon_collector_autoscaling.yml sql_exporter.yml sql_exporter_autoscaling.yml
neon_collector.yml: $(jsonnet_files)
JSONNET_PATH=jsonnet:etc jsonnet \
--output-file etc/$@ \
--ext-str pg_version=$(PG_VERSION) \
etc/neon_collector.jsonnet
neon_collector_autoscaling.yml: $(jsonnet_files)
JSONNET_PATH=jsonnet:etc jsonnet \
--output-file etc/$@ \
--ext-str pg_version=$(PG_VERSION) \
etc/neon_collector_autoscaling.jsonnet
sql_exporter.yml: $(jsonnet_files)
JSONNET_PATH=etc jsonnet \
--output-file etc/$@ \
--tla-str collector_name=neon_collector \
--tla-str collector_file=neon_collector.yml \
--tla-str 'connection_string=postgresql://cloud_admin@127.0.0.1:5432/postgres?sslmode=disable&application_name=sql_exporter&pgaudit.log=none' \
etc/sql_exporter.jsonnet
sql_exporter_autoscaling.yml: $(jsonnet_files)
JSONNET_PATH=etc jsonnet \
--output-file etc/$@ \
--tla-str collector_name=neon_collector_autoscaling \
--tla-str collector_file=neon_collector_autoscaling.yml \
--tla-str 'connection_string=postgresql://cloud_admin@127.0.0.1:5432/postgres?sslmode=disable&application_name=sql_exporter_autoscaling&pgaudit.log=none' \
etc/sql_exporter.jsonnet
.PHONY: clean
clean:
$(RM) \
etc/neon_collector.yml \
etc/neon_collector_autoscaling.yml \
etc/sql_exporter.yml \
etc/sql_exporter_autoscaling.yml
.PHONY: jsonnetfmt-test
jsonnetfmt-test:
jsonnetfmt --test $(jsonnet_files)
.PHONY: jsonnetfmt-format
jsonnetfmt-format:
jsonnetfmt --in-place $(jsonnet_files)
.PHONY: manifest-schema-validation
manifest-schema-validation: ../build-tools/node_modules
npx --prefix=../build-tools/ jsonschema validate -d https://json-schema.org/draft/2020-12/schema manifest.schema.json manifest.yaml
../build-tools/node_modules: ../build-tools/package.json
cd ../build-tools && $(if $(CI),npm ci,npm install)
touch ../build-tools/node_modules

View File

@@ -1,21 +0,0 @@
This directory contains files that are needed to build the compute
images, or included in the compute images.
compute-node.Dockerfile
To build the compute image
vm-image-spec.yaml
Instructions for vm-builder, to turn the compute-node image into
corresponding vm-compute-node image.
etc/
Configuration files included in /etc in the compute image
patches/
Some extensions need to be patched to work with Neon. This
directory contains such patches. They are applied to the extension
sources in compute-node.Dockerfile
In addition to these, postgres itself, the neon postgres extension,
and compute_ctl are built and copied into the compute image by
compute-node.Dockerfile.

File diff suppressed because it is too large Load Diff

View File

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

View File

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

View File

@@ -1,60 +0,0 @@
{
collector_name: 'neon_collector',
metrics: [
import 'sql_exporter/checkpoints_req.libsonnet',
import 'sql_exporter/checkpoints_timed.libsonnet',
import 'sql_exporter/compute_backpressure_throttling_seconds_total.libsonnet',
import 'sql_exporter/compute_current_lsn.libsonnet',
import 'sql_exporter/compute_logical_snapshot_files.libsonnet',
import 'sql_exporter/compute_logical_snapshots_bytes.libsonnet',
import 'sql_exporter/compute_max_connections.libsonnet',
import 'sql_exporter/compute_pg_oldest_frozen_xid_age.libsonnet',
import 'sql_exporter/compute_pg_oldest_mxid_age.libsonnet',
import 'sql_exporter/compute_receive_lsn.libsonnet',
import 'sql_exporter/compute_subscriptions_count.libsonnet',
import 'sql_exporter/connection_counts.libsonnet',
import 'sql_exporter/db_total_size.libsonnet',
import 'sql_exporter/file_cache_read_wait_seconds_bucket.libsonnet',
import 'sql_exporter/file_cache_read_wait_seconds_count.libsonnet',
import 'sql_exporter/file_cache_read_wait_seconds_sum.libsonnet',
import 'sql_exporter/file_cache_write_wait_seconds_bucket.libsonnet',
import 'sql_exporter/file_cache_write_wait_seconds_count.libsonnet',
import 'sql_exporter/file_cache_write_wait_seconds_sum.libsonnet',
import 'sql_exporter/getpage_prefetch_discards_total.libsonnet',
import 'sql_exporter/getpage_prefetch_misses_total.libsonnet',
import 'sql_exporter/getpage_prefetch_requests_total.libsonnet',
import 'sql_exporter/getpage_prefetches_buffered.libsonnet',
import 'sql_exporter/getpage_sync_requests_total.libsonnet',
import 'sql_exporter/compute_getpage_stuck_requests_total.libsonnet',
import 'sql_exporter/compute_getpage_max_inflight_stuck_time_ms.libsonnet',
import 'sql_exporter/getpage_wait_seconds_bucket.libsonnet',
import 'sql_exporter/getpage_wait_seconds_count.libsonnet',
import 'sql_exporter/getpage_wait_seconds_sum.libsonnet',
import 'sql_exporter/lfc_approximate_working_set_size.libsonnet',
import 'sql_exporter/lfc_approximate_working_set_size_windows.libsonnet',
import 'sql_exporter/lfc_cache_size_limit.libsonnet',
import 'sql_exporter/lfc_chunk_size.libsonnet',
import 'sql_exporter/lfc_hits.libsonnet',
import 'sql_exporter/lfc_misses.libsonnet',
import 'sql_exporter/lfc_used.libsonnet',
import 'sql_exporter/lfc_used_pages.libsonnet',
import 'sql_exporter/lfc_writes.libsonnet',
import 'sql_exporter/logical_slot_restart_lsn.libsonnet',
import 'sql_exporter/max_cluster_size.libsonnet',
import 'sql_exporter/pageserver_disconnects_total.libsonnet',
import 'sql_exporter/pageserver_requests_sent_total.libsonnet',
import 'sql_exporter/pageserver_send_flushes_total.libsonnet',
import 'sql_exporter/pageserver_open_requests.libsonnet',
import 'sql_exporter/pg_stats_userdb.libsonnet',
import 'sql_exporter/replication_delay_bytes.libsonnet',
import 'sql_exporter/replication_delay_seconds.libsonnet',
import 'sql_exporter/retained_wal.libsonnet',
import 'sql_exporter/wal_is_lost.libsonnet',
],
queries: [
{
query_name: 'neon_perf_counters',
query: importstr 'sql_exporter/neon_perf_counters.sql',
},
],
}

View File

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

View File

@@ -1,32 +0,0 @@
[databases]
;; pgbouncer propagates application_name (if it's specified) to the server, but some
;; clients don't set it. We set default application_name=pgbouncer to make it
;; easier to identify pgbouncer connections in Postgres. If client sets
;; application_name, it will be used instead.
*=host=localhost port=5432 auth_user=cloud_admin application_name=pgbouncer
[pgbouncer]
listen_port=6432
listen_addr=0.0.0.0
auth_type=scram-sha-256
auth_user=cloud_admin
auth_dbname=postgres
client_tls_sslmode=disable
server_tls_sslmode=disable
pool_mode=transaction
max_client_conn=10000
default_pool_size=64
max_prepared_statements=0
admin_users=postgres
unix_socket_dir=/tmp/
unix_socket_mode=0777
; required for pgbouncer_exporter
ignore_startup_parameters=extra_float_digits
; pidfile for graceful termination
pidfile=/tmp/pgbouncer.pid
;; Disable connection logging. It produces a lot of logs that no one looks at,
;; and we can get similar log entries from the proxy too. We had incidents in
;; the past where the logging significantly stressed the log device or pgbouncer
;; itself.
log_connections=0
log_disconnections=0

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

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