Compare commits

..

1 Commits

Author SHA1 Message Date
Ivan Efremov
e27d674b8e Update anstream package and deps
Update because of cargo deny check error:
error[unsound]: Unsoundness in anstream
2024-12-04 18:22:31 +02:00
363 changed files with 5585 additions and 17267 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

@@ -24,4 +24,3 @@
!storage_controller/
!vendor/postgres-*/
!workspace_hack/
!debug-oom/

View File

@@ -21,7 +21,3 @@ config-variables:
- SLACK_UPCOMING_RELEASE_CHANNEL_ID
- DEV_AWS_OIDC_ROLE_ARN
- BENCHMARK_INGEST_TARGET_PROJECTID
- PGREGRESS_PG16_PROJECT_ID
- PGREGRESS_PG17_PROJECT_ID
- SLACK_ON_CALL_QA_STAGING_STREAM
- DEV_AWS_OIDC_ROLE_MANAGE_BENCHMARK_EC2_VMS_ARN

View File

@@ -7,9 +7,10 @@ inputs:
type: boolean
required: false
default: false
aws-oicd-role-arn:
description: 'OIDC role arn to interract with S3'
required: true
aws_oicd_role_arn:
description: 'the OIDC role arn to (re-)acquire for allure report upload - if not set call must acquire OIDC role'
required: false
default: ''
outputs:
base-url:
@@ -83,11 +84,12 @@ runs:
ALLURE_VERSION: 2.27.0
ALLURE_ZIP_SHA256: b071858fb2fa542c65d8f152c5c40d26267b2dfb74df1f1608a589ecca38e777
- uses: aws-actions/configure-aws-credentials@v4
if: ${{ !cancelled() }}
- name: (Re-)configure AWS credentials # necessary to upload reports to S3 after a long-running test
if: ${{ !cancelled() && (inputs.aws_oicd_role_arn != '') }}
uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: eu-central-1
role-to-assume: ${{ inputs.aws-oicd-role-arn }}
role-to-assume: ${{ inputs.aws_oicd_role_arn }}
role-duration-seconds: 3600 # 1 hour should be more than enough to upload report
# Potentially we could have several running build for the same key (for example, for the main branch), so we use improvised lock for this

View File

@@ -8,9 +8,10 @@ inputs:
unique-key:
description: 'string to distinguish different results in the same run'
required: true
aws-oicd-role-arn:
description: 'OIDC role arn to interract with S3'
required: true
aws_oicd_role_arn:
description: 'the OIDC role arn to (re-)acquire for allure report upload - if not set call must acquire OIDC role'
required: false
default: ''
runs:
using: "composite"
@@ -35,11 +36,12 @@ runs:
env:
REPORT_DIR: ${{ inputs.report-dir }}
- uses: aws-actions/configure-aws-credentials@v4
if: ${{ !cancelled() }}
- name: (Re-)configure AWS credentials # necessary to upload reports to S3 after a long-running test
if: ${{ !cancelled() && (inputs.aws_oicd_role_arn != '') }}
uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: eu-central-1
role-to-assume: ${{ inputs.aws-oicd-role-arn }}
role-to-assume: ${{ inputs.aws_oicd_role_arn }}
role-duration-seconds: 3600 # 1 hour should be more than enough to upload report
- name: Upload test results

View File

@@ -15,19 +15,10 @@ inputs:
prefix:
description: "S3 prefix. Default is '${GITHUB_RUN_ID}/${GITHUB_RUN_ATTEMPT}'"
required: false
aws-oicd-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-oicd-role-arn }}
role-duration-seconds: 3600
- name: Download artifact
id: download-artifact
shell: bash -euxo pipefail {0}

View File

@@ -48,9 +48,10 @@ inputs:
description: 'benchmark durations JSON'
required: false
default: '{}'
aws-oicd-role-arn:
description: 'OIDC role arn to interract with S3'
required: true
aws_oicd_role_arn:
description: 'the OIDC role arn to (re-)acquire for allure report upload - if not set call must acquire OIDC role'
required: false
default: ''
runs:
using: "composite"
@@ -61,7 +62,6 @@ runs:
with:
name: neon-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build_type }}-artifact
path: /tmp/neon
aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}
- name: Download Neon binaries for the previous release
if: inputs.build_type != 'remote'
@@ -70,7 +70,6 @@ runs:
name: neon-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build_type }}-artifact
path: /tmp/neon-previous
prefix: latest
aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}
- name: Download compatibility snapshot
if: inputs.build_type != 'remote'
@@ -82,7 +81,6 @@ 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-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}
- name: Checkout
if: inputs.needs_postgres_source == 'true'
@@ -220,19 +218,17 @@ runs:
# The lack of compatibility snapshot shouldn't fail the job
# (for example if we didn't run the test for non build-and-test workflow)
skip-if-does-not-exist: true
aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}
- uses: aws-actions/configure-aws-credentials@v4
if: ${{ !cancelled() }}
- name: (Re-)configure AWS credentials # necessary to upload reports to S3 after a long-running test
if: ${{ !cancelled() && (inputs.aws_oicd_role_arn != '') }}
uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: eu-central-1
role-to-assume: ${{ inputs.aws-oicd-role-arn }}
role-to-assume: ${{ inputs.aws_oicd_role_arn }}
role-duration-seconds: 3600 # 1 hour should be more than enough to upload report
- name: Upload test results
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-store
with:
report-dir: /tmp/test_output/allure/results
unique-key: ${{ inputs.build_type }}-${{ inputs.pg_version }}
aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}

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-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}
- name: Upload coverage data
uses: ./.github/actions/upload
with:
name: coverage-data-artifact
path: /tmp/coverage
aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}

View File

@@ -14,10 +14,6 @@ inputs:
prefix:
description: "S3 prefix. Default is '${GITHUB_SHA}/${GITHUB_RUN_ID}/${GITHUB_RUN_ATTEMPT}'"
required: false
aws-oicd-role-arn:
description: "the OIDC role arn for aws auth"
required: false
default: ""
runs:
using: "composite"
@@ -57,13 +53,6 @@ runs:
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-oicd-role-arn }}
role-duration-seconds: 3600
- name: Upload artifact
if: ${{ steps.prepare-artifact.outputs.SKIPPED == 'false' }}
shell: bash -euxo pipefail {0}

View File

@@ -1,12 +0,0 @@
rust_code: ['**/*.rs', '**/Cargo.toml', '**/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

@@ -70,7 +70,6 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
# we create a table that has one row for each database that we want to restore with the status whether the restore is done
- name: Create benchmark_restore_status table if it does not exist

View File

@@ -31,13 +31,12 @@ defaults:
env:
RUST_BACKTRACE: 1
COPT: '-Werror'
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
container:
image: ${{ inputs.build-tools-image }}
credentials:
@@ -206,13 +205,6 @@ jobs:
done
fi
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 18000 # 5 hours
- name: Run rust tests
env:
NEXTEST_RETRIES: 3
@@ -264,7 +256,6 @@ jobs:
with:
name: neon-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-artifact
path: /tmp/neon
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
# XXX: keep this after the binaries.list is formed, so the coverage can properly work later
- name: Merge and upload coverage data
@@ -274,10 +265,6 @@ 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')) }}
container:
@@ -296,7 +283,7 @@ jobs:
submodules: true
- name: Pytest regression tests
continue-on-error: ${{ matrix.lfc_state == 'with-lfc' && inputs.build-type == 'debug' }}
continue-on-error: ${{ matrix.lfc_state == 'with-lfc' }}
uses: ./.github/actions/run-python-test-set
timeout-minutes: 60
with:
@@ -308,7 +295,6 @@ jobs:
real_s3_region: eu-central-1
rerun_failed: true
pg_version: ${{ matrix.pg_version }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
TEST_RESULT_CONNSTR: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
CHECK_ONDISK_DATA_COMPATIBILITY: nonempty

View File

@@ -33,7 +33,7 @@ jobs:
# 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

@@ -105,7 +105,6 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Create Neon Project
id: create-neon-project
@@ -123,7 +122,7 @@ jobs:
run_in_parallel: false
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
pg_version: ${{ env.DEFAULT_PG_VERSION }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
# Set --sparse-ordering option of pytest-order plugin
# to ensure tests are running in order of appears in the file.
# It's important for test_perf_pgbench.py::test_pgbench_remote_* tests
@@ -153,7 +152,7 @@ jobs:
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
with:
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
@@ -205,7 +204,6 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Run Logical Replication benchmarks
uses: ./.github/actions/run-python-test-set
@@ -216,7 +214,7 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 5400
pg_version: ${{ env.DEFAULT_PG_VERSION }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
@@ -233,7 +231,7 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 5400
pg_version: ${{ env.DEFAULT_PG_VERSION }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
@@ -245,7 +243,7 @@ jobs:
uses: ./.github/actions/allure-report-generate
with:
store-test-results-into-db: true
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
@@ -308,7 +306,6 @@ jobs:
"image": [ "'"$image_default"'" ],
"include": [{ "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-freetier", "db_size": "3gb" ,"runner": '"$runner_default"', "image": "'"$image_default"'" },
{ "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-new", "db_size": "10gb","runner": '"$runner_default"', "image": "'"$image_default"'" },
{ "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-new-many-tables","db_size": "10gb","runner": '"$runner_default"', "image": "'"$image_default"'" },
{ "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-new", "db_size": "50gb","runner": '"$runner_default"', "image": "'"$image_default"'" },
{ "pg_version": 16, "region_id": "azure-eastus2", "platform": "neonvm-azure-captest-freetier", "db_size": "3gb" ,"runner": '"$runner_azure"', "image": "neondatabase/build-tools:pinned-bookworm" },
{ "pg_version": 16, "region_id": "azure-eastus2", "platform": "neonvm-azure-captest-new", "db_size": "10gb","runner": '"$runner_azure"', "image": "neondatabase/build-tools:pinned-bookworm" },
@@ -408,10 +405,9 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Create Neon Project
if: contains(fromJson('["neonvm-captest-new", "neonvm-captest-new-many-tables", "neonvm-captest-freetier", "neonvm-azure-captest-freetier", "neonvm-azure-captest-new"]'), matrix.platform)
if: contains(fromJson('["neonvm-captest-new", "neonvm-captest-freetier", "neonvm-azure-captest-freetier", "neonvm-azure-captest-new"]'), matrix.platform)
id: create-neon-project
uses: ./.github/actions/neon-project-create
with:
@@ -430,7 +426,7 @@ jobs:
neonvm-captest-sharding-reuse)
CONNSTR=${{ secrets.BENCHMARK_CAPTEST_SHARDING_CONNSTR }}
;;
neonvm-captest-new | neonvm-captest-new-many-tables | neonvm-captest-freetier | neonvm-azure-captest-new | neonvm-azure-captest-freetier)
neonvm-captest-new | neonvm-captest-freetier | neonvm-azure-captest-new | neonvm-azure-captest-freetier)
CONNSTR=${{ steps.create-neon-project.outputs.dsn }}
;;
rds-aurora)
@@ -447,26 +443,6 @@ jobs:
echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
# we want to compare Neon project OLTP throughput and latency at scale factor 10 GB
# without (neonvm-captest-new)
# and with (neonvm-captest-new-many-tables) many relations in the database
- name: Create many relations before the run
if: contains(fromJson('["neonvm-captest-new-many-tables"]'), matrix.platform)
uses: ./.github/actions/run-python-test-set
with:
build_type: ${{ env.BUILD_TYPE }}
test_selection: performance
run_in_parallel: false
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_perf_many_relations
pg_version: ${{ env.DEFAULT_PG_VERSION }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
TEST_NUM_RELATIONS: 10000
- name: Benchmark init
uses: ./.github/actions/run-python-test-set
with:
@@ -476,7 +452,7 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_init
pg_version: ${{ env.DEFAULT_PG_VERSION }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
@@ -491,7 +467,7 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_simple_update
pg_version: ${{ env.DEFAULT_PG_VERSION }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
@@ -506,7 +482,7 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_pgbench_remote_select_only
pg_version: ${{ env.DEFAULT_PG_VERSION }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
@@ -524,7 +500,7 @@ jobs:
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
with:
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
@@ -635,7 +611,7 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_pgvector_indexing
pg_version: ${{ env.DEFAULT_PG_VERSION }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
@@ -650,7 +626,7 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600
pg_version: ${{ env.DEFAULT_PG_VERSION }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr }}
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
@@ -661,7 +637,7 @@ jobs:
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
with:
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
@@ -732,7 +708,6 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Set up Connection String
id: set-up-connstr
@@ -764,7 +739,7 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 43200 -k test_clickbench
pg_version: ${{ env.DEFAULT_PG_VERSION }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
@@ -778,7 +753,7 @@ jobs:
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
with:
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
@@ -843,7 +818,6 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Get Connstring Secret Name
run: |
@@ -882,7 +856,7 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_tpch
pg_version: ${{ env.DEFAULT_PG_VERSION }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
@@ -894,7 +868,7 @@ jobs:
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
with:
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
@@ -952,7 +926,6 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Set up Connection String
id: set-up-connstr
@@ -984,7 +957,7 @@ jobs:
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_user_examples
pg_version: ${{ env.DEFAULT_PG_VERSION }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
@@ -995,7 +968,7 @@ jobs:
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
with:
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}

View File

@@ -1,241 +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
jobs:
build-pgxn:
if: |
(inputs.pg_versions != '[]' || inputs.rebuild_everything) && (
contains(github.event.pull_request.labels.*.name, 'run-extra-build-macos') ||
contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
github.ref_name == 'main'
)
timeout-minutes: 30
runs-on: macos-15
strategy:
matrix:
postgres-version: ${{ inputs.rebuild_everything && fromJson('["v14", "v15", "v16", "v17"]') || fromJSON(inputs.pg_versions) }}
env:
# Use release build only, to have less debug info around
# Hence keeping target/ (and general cache size) smaller
BUILD_TYPE: release
steps:
- name: Checkout main repo
uses: actions/checkout@v4
- name: Set pg ${{ matrix.postgres-version }} for caching
id: pg_rev
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-${{ matrix.postgres-version }}) | tee -a "${GITHUB_OUTPUT}"
- name: Cache postgres ${{ matrix.postgres-version }} build
id: cache_pg
uses: actions/cache@v4
with:
path: pg_install/${{ matrix.postgres-version }}
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-${{ matrix.postgres-version }}-${{ steps.pg_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Checkout submodule vendor/postgres-${{ matrix.postgres-version }}
if: steps.cache_pg.outputs.cache-hit != 'true'
run: |
git submodule init vendor/postgres-${{ matrix.postgres-version }}
git submodule update --depth 1 --recursive
- name: Install build dependencies
if: steps.cache_pg.outputs.cache-hit != 'true'
run: |
brew install flex bison openssl protobuf icu4c
- name: Set extra env for macOS
if: steps.cache_pg.outputs.cache-hit != 'true'
run: |
echo 'LDFLAGS=-L/usr/local/opt/openssl@3/lib' >> $GITHUB_ENV
echo 'CPPFLAGS=-I/usr/local/opt/openssl@3/include' >> $GITHUB_ENV
- name: Build Postgres ${{ matrix.postgres-version }}
if: steps.cache_pg.outputs.cache-hit != 'true'
run: |
make postgres-${{ matrix.postgres-version }} -j$(sysctl -n hw.ncpu)
- name: Build Neon Pg Ext ${{ matrix.postgres-version }}
if: steps.cache_pg.outputs.cache-hit != 'true'
run: |
make "neon-pg-ext-${{ matrix.postgres-version }}" -j$(sysctl -n hw.ncpu)
- name: Get postgres headers ${{ matrix.postgres-version }}
if: steps.cache_pg.outputs.cache-hit != 'true'
run: |
make postgres-headers-${{ matrix.postgres-version }} -j$(sysctl -n hw.ncpu)
build-walproposer-lib:
if: |
(inputs.pg_versions != '[]' || inputs.rebuild_everything) && (
contains(github.event.pull_request.labels.*.name, 'run-extra-build-macos') ||
contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
github.ref_name == 'main'
)
timeout-minutes: 30
runs-on: macos-15
needs: [build-pgxn]
env:
# Use release build only, to have less debug info around
# Hence keeping target/ (and general cache size) smaller
BUILD_TYPE: release
steps:
- name: Checkout main repo
uses: actions/checkout@v4
- name: Set pg v17 for caching
id: pg_rev
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v17) | tee -a "${GITHUB_OUTPUT}"
- name: Cache postgres v17 build
id: cache_pg
uses: actions/cache@v4
with:
path: pg_install/v17
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-v17-${{ steps.pg_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Cache walproposer-lib
id: cache_walproposer_lib
uses: actions/cache@v4
with:
path: pg_install/build/walproposer-lib
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-walproposer_lib-v17-${{ steps.pg_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Checkout submodule vendor/postgres-v17
if: steps.cache_walproposer_lib.outputs.cache-hit != 'true'
run: |
git submodule init vendor/postgres-v17
git submodule update --depth 1 --recursive
- name: Install build dependencies
if: steps.cache_walproposer_lib.outputs.cache-hit != 'true'
run: |
brew install flex bison openssl protobuf icu4c
- name: Set extra env for macOS
if: steps.cache_walproposer_lib.outputs.cache-hit != 'true'
run: |
echo 'LDFLAGS=-L/usr/local/opt/openssl@3/lib' >> $GITHUB_ENV
echo 'CPPFLAGS=-I/usr/local/opt/openssl@3/include' >> $GITHUB_ENV
- name: Build walproposer-lib (only for v17)
if: steps.cache_walproposer_lib.outputs.cache-hit != 'true'
run:
make walproposer-lib -j$(sysctl -n hw.ncpu)
cargo-build:
if: |
(inputs.pg_versions != '[]' || inputs.rebuild_rust_code || inputs.rebuild_everything) && (
contains(github.event.pull_request.labels.*.name, 'run-extra-build-macos') ||
contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
github.ref_name == 'main'
)
timeout-minutes: 30
runs-on: macos-15
needs: [build-pgxn, build-walproposer-lib]
env:
# Use release build only, to have less debug info around
# Hence keeping target/ (and general cache size) smaller
BUILD_TYPE: release
steps:
- name: Checkout main repo
uses: actions/checkout@v4
with:
submodules: true
- name: Set pg v14 for caching
id: pg_rev_v14
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v14) | tee -a "${GITHUB_OUTPUT}"
- name: Set pg v15 for caching
id: pg_rev_v15
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v15) | tee -a "${GITHUB_OUTPUT}"
- name: Set pg v16 for caching
id: pg_rev_v16
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v16) | tee -a "${GITHUB_OUTPUT}"
- name: Set pg v17 for caching
id: pg_rev_v17
run: echo pg_rev=$(git rev-parse HEAD:vendor/postgres-v17) | tee -a "${GITHUB_OUTPUT}"
- name: Cache postgres v14 build
id: cache_pg
uses: actions/cache@v4
with:
path: pg_install/v14
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-v14-${{ steps.pg_rev_v14.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Cache postgres v15 build
id: cache_pg_v15
uses: actions/cache@v4
with:
path: pg_install/v15
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-v15-${{ steps.pg_rev_v15.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Cache postgres v16 build
id: cache_pg_v16
uses: actions/cache@v4
with:
path: pg_install/v16
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-v16-${{ steps.pg_rev_v16.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Cache postgres v17 build
id: cache_pg_v17
uses: actions/cache@v4
with:
path: pg_install/v17
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-v17-${{ steps.pg_rev_v17.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Cache cargo deps (only for v17)
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: Cache walproposer-lib
id: cache_walproposer_lib
uses: actions/cache@v4
with:
path: pg_install/build/walproposer-lib
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-walproposer_lib-v17-${{ steps.pg_rev_v17.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Install build dependencies
run: |
brew install flex bison openssl protobuf icu4c
- 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' >> $GITHUB_ENV
- name: Run cargo build (only for v17)
run: PQ_LIB_DIR=$(pwd)/pg_install/v17/lib cargo build --all --release -j$(sysctl -n hw.ncpu)
- name: Check that no warnings are produced (only for v17)
run: ./run_clippy.sh

View File

@@ -21,6 +21,8 @@ concurrency:
env:
RUST_BACKTRACE: 1
COPT: '-Werror'
AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
# A concurrency group that we use for e2e-tests runs, matches `concurrency.group` above with `github.repository` as a prefix
E2E_CONCURRENCY_GROUP: ${{ github.repository }}-e2e-tests-${{ github.ref_name }}-${{ github.ref_name == 'main' && github.sha || 'anysha' }}
@@ -212,7 +214,7 @@ jobs:
fi
echo "CLIPPY_COMMON_ARGS=${CLIPPY_COMMON_ARGS}" >> $GITHUB_ENV
- name: Run cargo clippy (debug)
run: cargo hack --features default --ignore-unknown-features --feature-powerset clippy $CLIPPY_COMMON_ARGS
run: cargo hack --feature-powerset clippy $CLIPPY_COMMON_ARGS
- name: Check documentation generation
run: cargo doc --workspace --no-deps --document-private-items
@@ -253,15 +255,15 @@ jobs:
build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
build-tag: ${{ needs.tag.outputs.build-tag }}
build-type: ${{ matrix.build-type }}
# Run tests on all Postgres versions in release builds and only on the latest version in debug builds.
# Run without LFC on v17 release and debug builds only. For all the other cases LFC is enabled.
# Run tests on all Postgres versions in release builds and only on the latest version in debug builds
# run without LFC on v17 release only
test-cfg: |
${{ matrix.build-type == 'release' && '[{"pg_version":"v14", "lfc_state": "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":"v17", "lfc_state": "without-lfc"}]'
|| '[{"pg_version":"v17", "lfc_state": "without-lfc" }]' }}
${{ matrix.build-type == 'release' && '[{"pg_version":"v14", "lfc_state": "without-lfc"},
{"pg_version":"v15", "lfc_state": "without-lfc"},
{"pg_version":"v16", "lfc_state": "without-lfc"},
{"pg_version":"v17", "lfc_state": "without-lfc"},
{"pg_version":"v17", "lfc_state": "with-lfc"}]'
|| '[{"pg_version":"v17", "lfc_state": "without-lfc"}]' }}
secrets: inherit
# Keep `benchmarks` job outside of `build-and-test-locally` workflow to make job failures non-blocking
@@ -303,11 +305,6 @@ jobs:
benchmarks:
if: github.ref_name == 'main' || contains(github.event.pull_request.labels.*.name, 'run-benchmarks')
needs: [ check-permissions, build-and-test-locally, build-build-tools-image, get-benchmarks-durations ]
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: write
pull-requests: write
runs-on: [ self-hosted, small ]
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
@@ -336,7 +333,6 @@ jobs:
extra_params: --splits 5 --group ${{ matrix.pytest_split_group }}
benchmark_durations: ${{ needs.get-benchmarks-durations.outputs.json }}
pg_version: v16
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
@@ -349,11 +345,6 @@ jobs:
report-benchmarks-failures:
needs: [ benchmarks, create-test-report ]
if: github.ref_name == 'main' && failure() && needs.benchmarks.result == 'failure'
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: write
pull-requests: write
runs-on: ubuntu-22.04
steps:
@@ -369,11 +360,6 @@ jobs:
create-test-report:
needs: [ check-permissions, build-and-test-locally, coverage-report, build-build-tools-image, benchmarks ]
if: ${{ !cancelled() && contains(fromJSON('["skipped", "success"]'), needs.check-permissions.result) }}
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 }}
@@ -394,7 +380,6 @@ jobs:
uses: ./.github/actions/allure-report-generate
with:
store-test-results-into-db: true
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
@@ -426,10 +411,6 @@ jobs:
coverage-report:
if: ${{ !startsWith(github.ref_name, 'release') }}
needs: [ check-permissions, build-build-tools-image, build-and-test-locally ]
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: write
runs-on: [ self-hosted, small ]
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
@@ -456,14 +437,12 @@ jobs:
with:
name: neon-${{ runner.os }}-${{ runner.arch }}-${{ matrix.build_type }}-artifact
path: /tmp/neon
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Get coverage artifact
uses: ./.github/actions/download
with:
name: coverage-data-artifact
path: /tmp/coverage
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Merge coverage data
run: scripts/coverage "--profraw-prefix=$GITHUB_JOB" --dir=/tmp/coverage merge
@@ -538,7 +517,7 @@ jobs:
trigger-e2e-tests:
if: ${{ !github.event.pull_request.draft || contains( github.event.pull_request.labels.*.name, 'run-e2e-tests-in-draft') || github.ref_name == 'main' || github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute' }}
needs: [ check-permissions, promote-images-dev, tag ]
needs: [ check-permissions, promote-images, tag ]
uses: ./.github/workflows/trigger-e2e-tests.yml
secrets: inherit
@@ -594,10 +573,6 @@ jobs:
neon-image:
needs: [ neon-image-arch, tag ]
runs-on: ubuntu-22.04
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: read
steps:
- uses: docker/login-action@v3
@@ -612,15 +587,11 @@ jobs:
neondatabase/neon:${{ needs.tag.outputs.build-tag }}-bookworm-x64 \
neondatabase/neon:${{ needs.tag.outputs.build-tag }}-bookworm-arm64
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
- uses: docker/login-action@v3
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 3600
- name: Login to Amazon Dev ECR
uses: aws-actions/amazon-ecr-login@v2
registry: 369495373322.dkr.ecr.eu-central-1.amazonaws.com
username: ${{ secrets.AWS_ACCESS_KEY_DEV }}
password: ${{ secrets.AWS_SECRET_KEY_DEV }}
- name: Push multi-arch image to ECR
run: |
@@ -629,10 +600,6 @@ jobs:
compute-node-image-arch:
needs: [ check-permissions, build-build-tools-image, tag ]
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: read
strategy:
fail-fast: false
matrix:
@@ -673,15 +640,11 @@ jobs:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
- uses: docker/login-action@v3
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 3600
- name: Login to Amazon Dev ECR
uses: aws-actions/amazon-ecr-login@v2
registry: 369495373322.dkr.ecr.eu-central-1.amazonaws.com
username: ${{ secrets.AWS_ACCESS_KEY_DEV }}
password: ${{ secrets.AWS_SECRET_KEY_DEV }}
- uses: docker/login-action@v3
with:
@@ -754,10 +717,6 @@ jobs:
compute-node-image:
needs: [ compute-node-image-arch, tag ]
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: read
runs-on: ubuntu-22.04
strategy:
@@ -802,15 +761,11 @@ jobs:
neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-x64 \
neondatabase/compute-tools:${{ needs.tag.outputs.build-tag }}-${{ matrix.version.debian }}-arm64
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
- uses: docker/login-action@v3
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 3600
- name: Login to Amazon Dev ECR
uses: aws-actions/amazon-ecr-login@v2
registry: 369495373322.dkr.ecr.eu-central-1.amazonaws.com
username: ${{ secrets.AWS_ACCESS_KEY_DEV }}
password: ${{ secrets.AWS_SECRET_KEY_DEV }}
- name: Push multi-arch compute-node-${{ matrix.version.pg }} image to ECR
run: |
@@ -840,7 +795,7 @@ jobs:
- pg: v17
debian: bookworm
env:
VM_BUILDER_VERSION: v0.37.1
VM_BUILDER_VERSION: v0.35.0
steps:
- uses: actions/checkout@v4
@@ -930,14 +885,12 @@ jobs:
docker compose -f ./docker-compose/docker-compose.yml logs || 0
docker compose -f ./docker-compose/docker-compose.yml down
promote-images-dev:
needs: [ check-permissions, tag, vm-compute-node-image ]
promote-images:
needs: [ check-permissions, tag, test-images, vm-compute-node-image ]
runs-on: ubuntu-22.04
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: read
id-token: write # for `aws-actions/configure-aws-credentials`
env:
VERSIONS: v14 v15 v16 v17
@@ -948,15 +901,12 @@ jobs:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
- name: Login to dev ECR
uses: docker/login-action@v3
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 3600
- name: Login to Amazon Dev ECR
uses: aws-actions/amazon-ecr-login@v2
registry: 369495373322.dkr.ecr.eu-central-1.amazonaws.com
username: ${{ secrets.AWS_ACCESS_KEY_DEV }}
password: ${{ secrets.AWS_SECRET_KEY_DEV }}
- name: Copy vm-compute-node images to ECR
run: |
@@ -965,35 +915,6 @@ jobs:
neondatabase/vm-compute-node-${version}:${{ needs.tag.outputs.build-tag }}
done
promote-images-prod:
needs: [ check-permissions, tag, test-images, vm-compute-node-image ]
runs-on: ubuntu-22.04
if: github.ref_name == 'main' || github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: read
env:
VERSIONS: v14 v15 v16 v17
steps:
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 3600
- name: Login to Amazon Dev ECR
uses: aws-actions/amazon-ecr-login@v2
- uses: docker/login-action@v3
with:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
- name: Add latest tag to images
if: github.ref_name == 'main'
run: |
@@ -1039,7 +960,7 @@ jobs:
push-to-acr-dev:
if: github.ref_name == 'main'
needs: [ tag, promote-images-dev ]
needs: [ tag, promote-images ]
uses: ./.github/workflows/_push-to-acr.yml
with:
client_id: ${{ vars.AZURE_DEV_CLIENT_ID }}
@@ -1051,7 +972,7 @@ jobs:
push-to-acr-prod:
if: github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
needs: [ tag, promote-images-prod ]
needs: [ tag, promote-images ]
uses: ./.github/workflows/_push-to-acr.yml
with:
client_id: ${{ vars.AZURE_PROD_CLIENT_ID }}
@@ -1064,11 +985,6 @@ jobs:
trigger-custom-extensions-build-and-wait:
needs: [ check-permissions, tag ]
runs-on: ubuntu-22.04
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: write
pull-requests: write
steps:
- name: Set PR's status to pending and request a remote CI test
run: |
@@ -1141,82 +1057,15 @@ jobs:
exit 1
deploy:
needs: [ check-permissions, promote-images-prod, tag, build-and-test-locally, trigger-custom-extensions-build-and-wait, push-to-acr-dev, push-to-acr-prod ]
needs: [ check-permissions, promote-images, tag, build-and-test-locally, trigger-custom-extensions-build-and-wait, push-to-acr-dev, push-to-acr-prod ]
# `!failure() && !cancelled()` is required because the workflow depends on the job that can be skipped: `push-to-acr-dev` and `push-to-acr-prod`
if: (github.ref_name == 'main' || github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute') && !failure() && !cancelled()
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: write
runs-on: [ self-hosted, small ]
container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/ansible:latest
steps:
- uses: actions/checkout@v4
- name: Create git tag and GitHub release
if: github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
uses: actions/github-script@v7
with:
retries: 5
script: |
const tag = "${{ needs.tag.outputs.build-tag }}";
try {
const existingRef = await github.rest.git.getRef({
owner: context.repo.owner,
repo: context.repo.repo,
ref: `tags/${tag}`,
});
if (existingRef.data.object.sha !== context.sha) {
throw new Error(`Tag ${tag} already exists but points to a different commit (expected: ${context.sha}, actual: ${existingRef.data.object.sha}).`);
}
console.log(`Tag ${tag} already exists and points to ${context.sha} as expected.`);
} catch (error) {
if (error.status !== 404) {
throw error;
}
console.log(`Tag ${tag} does not exist. Creating it...`);
await github.rest.git.createRef({
owner: context.repo.owner,
repo: context.repo.repo,
ref: `refs/tags/${tag}`,
sha: context.sha,
});
console.log(`Tag ${tag} created successfully.`);
}
// TODO: check how GitHub releases looks for proxy/compute releases and enable them if they're ok
if (context.ref !== 'refs/heads/release') {
console.log(`GitHub release skipped for ${context.ref}.`);
return;
}
try {
const existingRelease = await github.rest.repos.getReleaseByTag({
owner: context.repo.owner,
repo: context.repo.repo,
tag: tag,
});
console.log(`Release for tag ${tag} already exists (ID: ${existingRelease.data.id}).`);
} catch (error) {
if (error.status !== 404) {
throw error;
}
console.log(`Release for tag ${tag} does not exist. Creating it...`);
await github.rest.repos.createRelease({
owner: context.repo.owner,
repo: context.repo.repo,
tag_name: tag,
generate_release_notes: true,
});
console.log(`Release for tag ${tag} created successfully.`);
}
- name: Trigger deploy workflow
env:
GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
@@ -1266,13 +1115,38 @@ jobs:
exit 1
fi
- name: Create git tag
if: github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
uses: actions/github-script@v7
with:
# Retry script for 5XX server errors: https://github.com/actions/github-script#retries
retries: 5
script: |
await github.rest.git.createRef({
owner: context.repo.owner,
repo: context.repo.repo,
ref: "refs/tags/${{ needs.tag.outputs.build-tag }}",
sha: context.sha,
})
# TODO: check how GitHub releases looks for proxy releases and enable it if it's ok
- name: Create GitHub release
if: github.ref_name == 'release'
uses: actions/github-script@v7
with:
# Retry script for 5XX server errors: https://github.com/actions/github-script#retries
retries: 5
script: |
await github.rest.repos.createRelease({
owner: context.repo.owner,
repo: context.repo.repo,
tag_name: "${{ needs.tag.outputs.build-tag }}",
generate_release_notes: true,
})
# The job runs on `release` branch and copies compatibility data and Neon artifact from the last *release PR* to the latest directory
promote-compatibility-data:
needs: [ deploy ]
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: read
# `!failure() && !cancelled()` is required because the workflow transitively depends on the job that can be skipped: `push-to-acr-dev` and `push-to-acr-prod`
if: github.ref_name == 'release' && !failure() && !cancelled()
@@ -1309,12 +1183,6 @@ jobs:
echo "run-id=${run_id}" | tee -a ${GITHUB_OUTPUT}
echo "commit-sha=${last_commit_sha}" | tee -a ${GITHUB_OUTPUT}
- uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 3600
- name: Promote compatibility snapshot and Neon artifact
env:
BUCKET: neon-github-public-dev
@@ -1362,7 +1230,7 @@ jobs:
done
pin-build-tools-image:
needs: [ build-build-tools-image, promote-images-prod, build-and-test-locally ]
needs: [ build-build-tools-image, promote-images, build-and-test-locally ]
if: github.ref_name == 'main'
uses: ./.github/workflows/pin-build-tools-image.yml
with:
@@ -1385,7 +1253,7 @@ jobs:
- build-and-test-locally
- check-codestyle-python
- check-codestyle-rust
- promote-images-dev
- promote-images
- test-images
- trigger-custom-extensions-build-and-wait
runs-on: ubuntu-22.04

View File

@@ -19,21 +19,15 @@ concurrency:
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
DEFAULT_PG_VERSION: 16
TEST_OUTPUT: /tmp/test_output
BUILD_TYPE: remote
strategy:
fail-fast: false
matrix:
pg-version: [16, 17]
AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
runs-on: us-east-2
container:
@@ -46,11 +40,9 @@ jobs:
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${PG_VERSION}.patch"
cd "vendor/postgres-v${DEFAULT_PG_VERSION}"
patch -p1 < "../../compute/patches/cloud_regress_pg${DEFAULT_PG_VERSION}.patch"
- name: Generate a random password
id: pwgen
@@ -63,9 +55,8 @@ jobs:
- 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
cd vendor/postgres-v"${DEFAULT_PG_VERSION}"/src/test/regress
for fname in sql/*.sql expected/*.out; do
sed -i.bak s/NEON_PASSWORD_PLACEHOLDER/"'${DBPASS}'"/ "${fname}"
done
@@ -81,46 +72,27 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oicd-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}}
pg_version: ${{ env.DEFAULT_PG_VERSION }}
extra_params: -m remote_cluster
aws-oicd-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}}
BENCHMARK_CONNSTR: ${{ secrets.PG_REGRESS_CONNSTR }}
- name: Create Allure report
id: create-allure-report
if: ${{ !cancelled() }}
uses: ./.github/actions/allure-report-generate
with:
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@v1
with:
channel-id: ${{ vars.SLACK_ON_CALL_QA_STAGING_STREAM }}
channel-id: "C033QLM5P7D" # on-call-staging-stream
slack-message: |
Periodic pg_regress on staging: ${{ job.status }}
<${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}|GitHub Run>

View File

@@ -13,7 +13,7 @@ on:
# │ │ │ │ ┌───────────── 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}
@@ -28,7 +28,7 @@ jobs:
strategy:
fail-fast: false # allow other variants to continue even if one fails
matrix:
target_project: [new_empty_project, large_existing_project]
target_project: [new_empty_project, large_existing_project]
permissions:
contents: write
statuses: write
@@ -56,7 +56,7 @@ jobs:
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 18000 # 5 hours is currently max associated with IAM role
role-duration-seconds: 18000 # 5 hours is currently max associated with IAM role
- name: Download Neon artifact
uses: ./.github/actions/download
@@ -64,7 +64,6 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Create Neon Project
if: ${{ matrix.target_project == 'new_empty_project' }}
@@ -95,7 +94,7 @@ jobs:
project_id: ${{ vars.BENCHMARK_INGEST_TARGET_PROJECTID }}
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
- name: Initialize Neon project
- name: Initialize Neon project
if: ${{ matrix.target_project == 'large_existing_project' }}
env:
BENCHMARK_INGEST_TARGET_CONNSTR: ${{ steps.create-neon-branch-ingest-target.outputs.dsn }}
@@ -123,7 +122,7 @@ jobs:
${PSQL} "${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
- name: Invoke pgcopydb
uses: ./.github/actions/run-python-test-set
with:
build_type: remote
@@ -132,7 +131,7 @@ jobs:
extra_params: -s -m remote_cluster --timeout 86400 -k test_ingest_performance_using_pgcopydb
pg_version: v16
save_perf_report: true
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
aws_oicd_role_arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
BENCHMARK_INGEST_SOURCE_CONNSTR: ${{ secrets.BENCHMARK_INGEST_SOURCE_CONNSTR }}
TARGET_PROJECT_TYPE: ${{ matrix.target_project }}
@@ -144,7 +143,7 @@ jobs:
run: |
export LD_LIBRARY_PATH=${PG_16_LIB_PATH}
${PSQL} "${BENCHMARK_INGEST_TARGET_CONNSTR}" -c "\dt+"
- name: Delete Neon Project
if: ${{ always() && matrix.target_project == 'new_empty_project' }}
uses: ./.github/actions/neon-project-delete

View File

@@ -31,15 +31,19 @@ jobs:
uses: ./.github/workflows/build-build-tools-image.yml
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: ${{ steps.files_changed.outputs.rebuild_neon_extra || steps.files_changed.outputs.rebuild_macos }}
check-macos-build:
needs: [ check-permissions ]
if: |
contains(github.event.pull_request.labels.*.name, 'run-extra-build-macos') ||
contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
github.ref_name == 'main'
timeout-minutes: 90
runs-on: macos-15
env:
# Use release build only, to have less debug info around
# Hence keeping target/ (and general cache size) smaller
BUILD_TYPE: release
steps:
- name: Checkout
@@ -47,45 +51,102 @@ jobs:
with:
submodules: true
- name: Check for Postgres changes
uses: dorny/paths-filter@1441771bbfdd59dcd748680ee64ebd8faab1a242 #v3
id: files_changed
- name: Install macOS postgres dependencies
run: brew install flex bison openssl protobuf icu4c
- name: Set pg 14 revision for caching
id: pg_v14_rev
run: echo pg_rev=$(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
- 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 ${{ steps.files_changed.outputs.chnages }} | jq '.[]|select(test("v\\d+"))' | jq --slurp -c)
echo "changes=${v_strings_only_as_json_array}" | tee -a "${GITHUB_OUTPUT}"
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 ]
if: |
contains(github.event.pull_request.labels.*.name, 'run-extra-build-macos') ||
contains(github.event.pull_request.labels.*.name, 'run-extra-build-*') ||
github.ref_name == 'main'
uses: ./.github/workflows/build-macos.yml
with:
pg_versions: ${{ needs.files-changed.outputs.postgres_changes }}
rebuild_rust_code: ${{ 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: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
@@ -116,18 +177,13 @@ jobs:
- name: Produce the build stats
run: PQ_LIB_DIR=$(pwd)/pg_install/v17/lib cargo build --all --release --timings -j$(nproc)
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 3600
- 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}/"

View File

@@ -27,11 +27,6 @@ concurrency:
jobs:
trigger_bench_on_ec2_machine_in_eu_central_1:
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: write
pull-requests: write
runs-on: [ self-hosted, small ]
container:
image: neondatabase/build-tools:pinned-bookworm
@@ -43,6 +38,8 @@ jobs:
env:
API_KEY: ${{ secrets.PERIODIC_PAGEBENCH_EC2_RUNNER_API_KEY }}
RUN_ID: ${{ github.run_id }}
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:
@@ -53,13 +50,6 @@ jobs:
- name: Show my own (github runner) external IP address - usefull for IP allowlisting
run: curl https://ifconfig.me
- name: Assume AWS OIDC role that allows to manage (start/stop/describe... EC machine)
uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_MANAGE_BENCHMARK_EC2_VMS_ARN }}
role-duration-seconds: 3600
- name: Start EC2 instance and wait for the instance to boot up
run: |
aws ec2 start-instances --instance-ids $AWS_INSTANCE_ID
@@ -134,10 +124,11 @@ jobs:
cat "test_log_${GITHUB_RUN_ID}"
- name: 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-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
@@ -157,14 +148,6 @@ jobs:
-H "Authorization: Bearer $API_KEY" \
-d ''
- name: Assume AWS OIDC role that allows to manage (start/stop/describe... EC machine)
if: always() && steps.poll_step.outputs.too_many_runs != 'true'
uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_MANAGE_BENCHMARK_EC2_VMS_ARN }}
role-duration-seconds: 3600
- name: Stop EC2 instance and wait for the instance to be stopped
if: always() && steps.poll_step.outputs.too_many_runs != 'true'
run: |

View File

@@ -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: 16
PLATFORM: neon-captest-new
AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_DEV }}
AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_KEY_DEV }}
AWS_DEFAULT_REGION: eu-central-1
jobs:
@@ -96,7 +94,6 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Create Neon Project
id: create-neon-project
@@ -113,7 +110,6 @@ jobs:
run_in_parallel: false
extra_params: -m remote_cluster
pg_version: ${{ env.DEFAULT_PG_VERSION }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
BENCHMARK_CONNSTR: ${{ steps.create-neon-project.outputs.dsn }}
@@ -130,7 +126,6 @@ jobs:
uses: ./.github/actions/allure-report-generate
with:
store-test-results-into-db: true
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
@@ -164,7 +159,6 @@ jobs:
name: neon-${{ runner.os }}-${{ runner.arch }}-release-artifact
path: /tmp/neon/
prefix: latest
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Create Neon Project
id: create-neon-project
@@ -181,7 +175,6 @@ jobs:
run_in_parallel: false
extra_params: -m remote_cluster
pg_version: ${{ env.DEFAULT_PG_VERSION }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
BENCHMARK_CONNSTR: ${{ steps.create-neon-project.outputs.dsn }}
@@ -198,7 +191,6 @@ jobs:
uses: ./.github/actions/allure-report-generate
with:
store-test-results-into-db: true
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}

View File

@@ -67,7 +67,7 @@ jobs:
runs-on: ubuntu-22.04
permissions:
id-token: write # for `azure/login` and aws auth
id-token: write # for `azure/login`
steps:
- uses: docker/login-action@v3
@@ -75,15 +75,11 @@ jobs:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
- uses: docker/login-action@v3
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 3600
- name: Login to Amazon Dev ECR
uses: aws-actions/amazon-ecr-login@v2
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

View File

@@ -63,7 +63,6 @@ jobs:
if: always()
permissions:
statuses: write # for `github.repos.createCommitStatus(...)`
contents: write
needs:
- get-changed-files
- check-codestyle-python

View File

@@ -3,7 +3,7 @@ name: Create Release Branch
on:
schedule:
# It should be kept in sync with if-condition in jobs
- cron: '0 6 * * FRI' # Storage release
- cron: '0 6 * * MON' # Storage release
- cron: '0 6 * * THU' # Proxy release
workflow_dispatch:
inputs:
@@ -29,7 +29,7 @@ defaults:
jobs:
create-storage-release-branch:
if: ${{ github.event.schedule == '0 6 * * FRI' || inputs.create-storage-release-branch }}
if: ${{ github.event.schedule == '0 6 * * MON' || inputs.create-storage-release-branch }}
permissions:
contents: write

View File

@@ -68,7 +68,7 @@ jobs:
GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
TAG: ${{ needs.tag.outputs.build-tag }}
steps:
- name: Wait for `promote-images-dev` job to finish
- name: Wait for `promote-images` job to finish
# It's important to have a timeout here, the script in the step can run infinitely
timeout-minutes: 60
run: |
@@ -79,17 +79,17 @@ jobs:
# For PRs we use the run id as the tag
BUILD_AND_TEST_RUN_ID=${TAG}
while true; do
conclusion=$(gh run --repo ${GITHUB_REPOSITORY} view ${BUILD_AND_TEST_RUN_ID} --json jobs --jq '.jobs[] | select(.name == "promote-images-dev") | .conclusion')
conclusion=$(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-dev' job didn't succeed: '${conclusion}'. Exiting..."
echo "The 'promote-images' job didn't succeed: '${conclusion}'. Exiting..."
exit 1
;;
*)
echo "The 'promote-images-dev' hasn't succeed yet. Waiting..."
echo "The 'promote-images' hasn't succeed yet. Waiting..."
sleep 60
;;
esac

View File

@@ -1,29 +1,16 @@
# Autoscaling
/libs/vm_monitor/ @neondatabase/autoscaling
# DevProd
/.github/ @neondatabase/developer-productivity
# Compute
/pgxn/ @neondatabase/compute
/vendor/ @neondatabase/compute
/compute/ @neondatabase/compute
/compute_tools/ @neondatabase/compute
# Proxy
/compute_tools/ @neondatabase/control-plane @neondatabase/compute
/libs/pageserver_api/ @neondatabase/storage
/libs/postgres_ffi/ @neondatabase/compute @neondatabase/storage
/libs/proxy/ @neondatabase/proxy
/proxy/ @neondatabase/proxy
# Storage
/libs/remote_storage/ @neondatabase/storage
/libs/safekeeper_api/ @neondatabase/storage
/libs/vm_monitor/ @neondatabase/autoscaling
/pageserver/ @neondatabase/storage
/pgxn/ @neondatabase/compute
/pgxn/neon/ @neondatabase/compute @neondatabase/storage
/proxy/ @neondatabase/proxy
/safekeeper/ @neondatabase/storage
/storage_controller @neondatabase/storage
/storage_scrubber @neondatabase/storage
/libs/pageserver_api/ @neondatabase/storage
/libs/remote_storage/ @neondatabase/storage
/libs/safekeeper_api/ @neondatabase/storage
# Shared
/pgxn/neon/ @neondatabase/compute @neondatabase/storage
/libs/compute_api/ @neondatabase/compute @neondatabase/control-plane
/libs/postgres_ffi/ @neondatabase/compute @neondatabase/storage
/vendor/ @neondatabase/compute

761
Cargo.lock generated

File diff suppressed because it is too large Load Diff

View File

@@ -11,7 +11,6 @@ members = [
"pageserver/pagebench",
"proxy",
"safekeeper",
"safekeeper/client",
"storage_broker",
"storage_controller",
"storage_controller/client",
@@ -52,7 +51,10 @@ anyhow = { version = "1.0", features = ["backtrace"] }
arc-swap = "1.6"
async-compression = { version = "0.4.0", features = ["tokio", "gzip", "zstd"] }
atomic-take = "1.1.0"
backtrace = "0.3.74"
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"
async-stream = "0.3"
async-trait = "0.1"
@@ -135,7 +137,7 @@ parquet = { version = "53", default-features = false, features = ["zstd"] }
parquet_derive = "53"
pbkdf2 = { version = "0.12.1", features = ["simple", "std"] }
pin-project-lite = "0.2"
pprof = { version = "0.14", features = ["criterion", "flamegraph", "frame-pointer", "protobuf", "protobuf-codec"] }
pprof = { version = "0.14", features = ["criterion", "flamegraph", "protobuf", "protobuf-codec"] }
procfs = "0.16"
prometheus = {version = "0.13", default-features=false, features = ["process"]} # removes protobuf dependency
prost = "0.13"
@@ -214,12 +216,6 @@ postgres-protocol = { git = "https://github.com/neondatabase/rust-postgres.git",
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"] }
## Local libraries
compute_api = { version = "0.1", path = "./libs/compute_api/" }
consumption_metrics = { version = "0.1", path = "./libs/consumption_metrics/" }
@@ -235,7 +231,6 @@ postgres_initdb = { path = "./libs/postgres_initdb" }
pq_proto = { version = "0.1", path = "./libs/pq_proto/" }
remote_storage = { version = "0.1", path = "./libs/remote_storage/" }
safekeeper_api = { version = "0.1", path = "./libs/safekeeper_api" }
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" }
@@ -266,8 +261,6 @@ tokio-postgres = { git = "https://github.com/neondatabase/rust-postgres.git", br
[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

@@ -45,7 +45,7 @@ COPY --chown=nonroot . .
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 -Cforce-frame-pointers=yes ${ADDITIONAL_RUSTFLAGS}" cargo build \
&& PQ_LIB_DIR=$(pwd)/pg_install/v${STABLE_PG_VERSION}/lib RUSTFLAGS="-Clinker=clang -Clink-arg=-fuse-ld=mold -Clink-arg=-Wl,--no-rosegment ${ADDITIONAL_RUSTFLAGS}" cargo build \
--bin pg_sni_router \
--bin pageserver \
--bin pagectl \
@@ -69,8 +69,6 @@ RUN set -e \
libreadline-dev \
libseccomp-dev \
ca-certificates \
# System postgres for use with client libraries (e.g. in storage controller)
postgresql-15 \
&& rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* \
&& useradd -d /data neon \
&& chown -R neon:neon /data
@@ -103,6 +101,11 @@ RUN mkdir -p /data/.neon/ && \
> /data/.neon/pageserver.toml && \
chown -R neon:neon /data/.neon
# When running a binary that links with libpq, default to using our most recent postgres version. Binaries
# that want a particular postgres version will select it explicitly: this is just a default.
ENV LD_LIBRARY_PATH=/usr/local/v${DEFAULT_PG_VERSION}/lib
VOLUME ["/data"]
USER neon
EXPOSE 6400

View File

@@ -115,7 +115,7 @@ RUN set -e \
# Keep the version the same as in compute/compute-node.Dockerfile and
# test_runner/regress/test_compute_metrics.py.
ENV SQL_EXPORTER_VERSION=0.16.0
ENV SQL_EXPORTER_VERSION=0.13.1
RUN curl -fsSL \
"https://github.com/burningalchemist/sql_exporter/releases/download/${SQL_EXPORTER_VERSION}/sql_exporter-${SQL_EXPORTER_VERSION}.linux-$(case "$(uname -m)" in x86_64) echo amd64;; aarch64) echo arm64;; esac).tar.gz" \
--output sql_exporter.tar.gz \

File diff suppressed because it is too large Load Diff

View File

@@ -3,10 +3,9 @@
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_backpressure_throttling_seconds.libsonnet',
import 'sql_exporter/compute_current_lsn.libsonnet',
import 'sql_exporter/compute_logical_snapshot_files.libsonnet',
import 'sql_exporter/compute_logical_snapshots_bytes.libsonnet',
import 'sql_exporter/compute_max_connections.libsonnet',
import 'sql_exporter/compute_receive_lsn.libsonnet',
import 'sql_exporter/compute_subscriptions_count.libsonnet',

View File

@@ -19,10 +19,3 @@ max_prepared_statements=0
admin_users=postgres
unix_socket_dir=/tmp/
unix_socket_mode=0777
;; 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

@@ -1,10 +1,10 @@
{
metric_name: 'compute_backpressure_throttling_seconds_total',
type: 'counter',
metric_name: 'compute_backpressure_throttling_seconds',
type: 'gauge',
help: 'Time compute has spent throttled',
key_labels: null,
values: [
'throttled',
],
query: importstr 'sql_exporter/compute_backpressure_throttling_seconds_total.sql',
query: importstr 'sql_exporter/compute_backpressure_throttling_seconds.sql',
}

View File

@@ -1,7 +0,0 @@
SELECT
(SELECT current_setting('neon.timeline_id')) AS timeline_id,
-- Postgres creates temporary snapshot files of the form %X-%X.snap.%d.tmp.
-- These temporary snapshot files are renamed to the actual snapshot files
-- after they are completely built. We only WAL-log the completely built
-- snapshot files
(SELECT COALESCE(sum(size), 0) FROM pg_ls_logicalsnapdir() WHERE name LIKE '%.snap') AS logical_snapshots_bytes;

View File

@@ -1,17 +0,0 @@
local neon = import 'neon.libsonnet';
local pg_ls_logicalsnapdir = importstr 'sql_exporter/compute_logical_snapshots_bytes.15.sql';
local pg_ls_dir = importstr 'sql_exporter/compute_logical_snapshots_bytes.sql';
{
metric_name: 'compute_logical_snapshots_bytes',
type: 'gauge',
help: 'Size of the pg_logical/snapshots directory, not including temporary files',
key_labels: [
'timeline_id',
],
values: [
'logical_snapshots_bytes',
],
query: if neon.PG_MAJORVERSION_NUM < 15 then pg_ls_dir else pg_ls_logicalsnapdir,
}

View File

@@ -1,9 +0,0 @@
SELECT
(SELECT setting FROM pg_settings WHERE name = 'neon.timeline_id') AS timeline_id,
-- Postgres creates temporary snapshot files of the form %X-%X.snap.%d.tmp.
-- These temporary snapshot files are renamed to the actual snapshot files
-- after they are completely built. We only WAL-log the completely built
-- snapshot files
(SELECT COALESCE(sum((pg_stat_file('pg_logical/snapshots/' || name, missing_ok => true)).size), 0)
FROM (SELECT * FROM pg_ls_dir('pg_logical/snapshots') WHERE pg_ls_dir LIKE '%.snap') AS name
) AS logical_snapshots_bytes;

View File

@@ -981,7 +981,7 @@ index fc42d418bf..e38f517574 100644
CREATE SCHEMA addr_nsp;
SET search_path TO 'addr_nsp';
diff --git a/src/test/regress/expected/password.out b/src/test/regress/expected/password.out
index 8475231735..0653946337 100644
index 8475231735..1afae5395f 100644
--- a/src/test/regress/expected/password.out
+++ b/src/test/regress/expected/password.out
@@ -12,11 +12,11 @@ SET password_encryption = 'md5'; -- ok
@@ -1006,63 +1006,65 @@ index 8475231735..0653946337 100644
-----------------+---------------------------------------------------
- regress_passwd1 | md5783277baca28003b33453252be4dbb34
- regress_passwd2 | md54044304ba511dd062133eb5b4b84a2a3
+ regress_passwd1 | NEON_MD5_PLACEHOLDER:regress_passwd1
+ regress_passwd2 | NEON_MD5_PLACEHOLDER:regress_passwd2
+ regress_passwd1 | NEON_MD5_PLACEHOLDER_regress_passwd1
+ regress_passwd2 | NEON_MD5_PLACEHOLDER_regress_passwd2
regress_passwd3 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
- regress_passwd4 |
+ regress_passwd4 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
(4 rows)
-- Rename a role
@@ -54,24 +54,16 @@ ALTER ROLE regress_passwd2_new RENAME TO regress_passwd2;
@@ -54,24 +54,30 @@ ALTER ROLE regress_passwd2_new RENAME TO regress_passwd2;
-- passwords.
SET password_encryption = 'md5';
-- encrypt with MD5
-ALTER ROLE regress_passwd2 PASSWORD 'foo';
--- already encrypted, use as they are
-ALTER ROLE regress_passwd1 PASSWORD 'md5cd3578025fe2c3d7ed1b9a9b26238b70';
-ALTER ROLE regress_passwd3 PASSWORD 'SCRAM-SHA-256$4096:VLK4RMaQLCvNtQ==$6YtlR4t69SguDiwFvbVgVZtuz6gpJQQqUMZ7IQJK5yI=:ps75jrHeYU4lXCcXI4O8oIdJ3eO8o2jirjruw9phBTo=';
+ALTER ROLE regress_passwd2 PASSWORD NEON_PASSWORD_PLACEHOLDER;
-- already encrypted, use as they are
ALTER ROLE regress_passwd1 PASSWORD 'md5cd3578025fe2c3d7ed1b9a9b26238b70';
+ERROR: Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
ALTER ROLE regress_passwd3 PASSWORD 'SCRAM-SHA-256$4096:VLK4RMaQLCvNtQ==$6YtlR4t69SguDiwFvbVgVZtuz6gpJQQqUMZ7IQJK5yI=:ps75jrHeYU4lXCcXI4O8oIdJ3eO8o2jirjruw9phBTo=';
+ERROR: Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
SET password_encryption = 'scram-sha-256';
-- create SCRAM secret
-ALTER ROLE regress_passwd4 PASSWORD 'foo';
--- already encrypted with MD5, use as it is
-CREATE ROLE regress_passwd5 PASSWORD 'md5e73a4b11df52a6068f8b39f90be36023';
--- This looks like a valid SCRAM-SHA-256 secret, but it is not
--- so it should be hashed with SCRAM-SHA-256.
-CREATE ROLE regress_passwd6 PASSWORD 'SCRAM-SHA-256$1234';
--- These may look like valid MD5 secrets, but they are not, so they
--- should be hashed with SCRAM-SHA-256.
--- trailing garbage at the end
-CREATE ROLE regress_passwd7 PASSWORD 'md5012345678901234567890123456789zz';
--- invalid length
-CREATE ROLE regress_passwd8 PASSWORD 'md501234567890123456789012345678901zz';
+ALTER ROLE regress_passwd4 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+-- Neon does not support encrypted passwords, use unencrypted instead
+CREATE ROLE regress_passwd5 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+-- Neon does not support encrypted passwords, use unencrypted instead
+CREATE ROLE regress_passwd6 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+CREATE ROLE regress_passwd7 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+CREATE ROLE regress_passwd8 PASSWORD NEON_PASSWORD_PLACEHOLDER;
-- already encrypted with MD5, use as it is
CREATE ROLE regress_passwd5 PASSWORD 'md5e73a4b11df52a6068f8b39f90be36023';
+ERROR: Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
-- This looks like a valid SCRAM-SHA-256 secret, but it is not
-- so it should be hashed with SCRAM-SHA-256.
CREATE ROLE regress_passwd6 PASSWORD 'SCRAM-SHA-256$1234';
+ERROR: Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
-- These may look like valid MD5 secrets, but they are not, so they
-- should be hashed with SCRAM-SHA-256.
-- trailing garbage at the end
CREATE ROLE regress_passwd7 PASSWORD 'md5012345678901234567890123456789zz';
+ERROR: Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
-- invalid length
CREATE ROLE regress_passwd8 PASSWORD 'md501234567890123456789012345678901zz';
+ERROR: Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
-- Changing the SCRAM iteration count
SET scram_iterations = 1024;
CREATE ROLE regress_passwd9 PASSWORD 'alterediterationcount';
@@ -81,11 +73,11 @@ SELECT rolname, regexp_replace(rolpassword, '(SCRAM-SHA-256)\$(\d+):([a-zA-Z0-9+
@@ -81,63 +87,67 @@ SELECT rolname, regexp_replace(rolpassword, '(SCRAM-SHA-256)\$(\d+):([a-zA-Z0-9+
ORDER BY rolname, rolpassword;
rolname | rolpassword_masked
-----------------+---------------------------------------------------
- regress_passwd1 | md5cd3578025fe2c3d7ed1b9a9b26238b70
- regress_passwd2 | md5dfa155cadd5f4ad57860162f3fab9cdb
+ regress_passwd1 | NEON_MD5_PLACEHOLDER:regress_passwd1
+ regress_passwd2 | NEON_MD5_PLACEHOLDER:regress_passwd2
+ regress_passwd1 | NEON_MD5_PLACEHOLDER_regress_passwd1
+ regress_passwd2 | NEON_MD5_PLACEHOLDER_regress_passwd2
regress_passwd3 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
regress_passwd4 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
- regress_passwd5 | md5e73a4b11df52a6068f8b39f90be36023
+ regress_passwd5 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
regress_passwd6 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
regress_passwd7 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
regress_passwd8 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
@@ -95,23 +87,20 @@ SELECT rolname, regexp_replace(rolpassword, '(SCRAM-SHA-256)\$(\d+):([a-zA-Z0-9+
- regress_passwd6 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
- regress_passwd7 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
- regress_passwd8 | SCRAM-SHA-256$4096:<salt>$<storedkey>:<serverkey>
regress_passwd9 | SCRAM-SHA-256$1024:<salt>$<storedkey>:<serverkey>
-(9 rows)
+(5 rows)
-- An empty password is not allowed, in any form
CREATE ROLE regress_passwd_empty PASSWORD '';
NOTICE: empty string is not a valid password, clearing password
@@ -1080,37 +1082,56 @@ index 8475231735..0653946337 100644
-(1 row)
+(0 rows)
--- Test with invalid stored and server keys.
---
--- The first is valid, to act as a control. The others have too long
--- stored/server keys. They will be re-hashed.
-CREATE ROLE regress_passwd_sha_len0 PASSWORD 'SCRAM-SHA-256$4096:A6xHKoH/494E941doaPOYg==$Ky+A30sewHIH3VHQLRN9vYsuzlgNyGNKCh37dy96Rqw=:COPdlNiIkrsacU5QoxydEuOH6e/KfiipeETb/bPw8ZI=';
-CREATE ROLE regress_passwd_sha_len1 PASSWORD 'SCRAM-SHA-256$4096:A6xHKoH/494E941doaPOYg==$Ky+A30sewHIH3VHQLRN9vYsuzlgNyGNKCh37dy96RqwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=:COPdlNiIkrsacU5QoxydEuOH6e/KfiipeETb/bPw8ZI=';
-CREATE ROLE regress_passwd_sha_len2 PASSWORD 'SCRAM-SHA-256$4096:A6xHKoH/494E941doaPOYg==$Ky+A30sewHIH3VHQLRN9vYsuzlgNyGNKCh37dy96Rqw=:COPdlNiIkrsacU5QoxydEuOH6e/KfiipeETb/bPw8ZIAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=';
+-- Neon does not support encrypted passwords, use unencrypted instead
+CREATE ROLE regress_passwd_sha_len0 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+CREATE ROLE regress_passwd_sha_len1 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+CREATE ROLE regress_passwd_sha_len2 PASSWORD NEON_PASSWORD_PLACEHOLDER;
-- Test with invalid stored and server keys.
--
-- The first is valid, to act as a control. The others have too long
-- stored/server keys. They will be re-hashed.
CREATE ROLE regress_passwd_sha_len0 PASSWORD 'SCRAM-SHA-256$4096:A6xHKoH/494E941doaPOYg==$Ky+A30sewHIH3VHQLRN9vYsuzlgNyGNKCh37dy96Rqw=:COPdlNiIkrsacU5QoxydEuOH6e/KfiipeETb/bPw8ZI=';
+ERROR: Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
CREATE ROLE regress_passwd_sha_len1 PASSWORD 'SCRAM-SHA-256$4096:A6xHKoH/494E941doaPOYg==$Ky+A30sewHIH3VHQLRN9vYsuzlgNyGNKCh37dy96RqwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=:COPdlNiIkrsacU5QoxydEuOH6e/KfiipeETb/bPw8ZI=';
+ERROR: Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
CREATE ROLE regress_passwd_sha_len2 PASSWORD 'SCRAM-SHA-256$4096:A6xHKoH/494E941doaPOYg==$Ky+A30sewHIH3VHQLRN9vYsuzlgNyGNKCh37dy96Rqw=:COPdlNiIkrsacU5QoxydEuOH6e/KfiipeETb/bPw8ZIAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=';
+ERROR: Received HTTP code 400 from control plane: {"error":"Neon only supports being given plaintext passwords"}
-- Check that the invalid secrets were re-hashed. A re-hashed secret
-- should not contain the original salt.
SELECT rolname, rolpassword not like '%A6xHKoH/494E941doaPOYg==%' as is_rolpassword_rehashed
@@ -120,7 +109,7 @@ SELECT rolname, rolpassword not like '%A6xHKoH/494E941doaPOYg==%' as is_rolpassw
FROM pg_authid
WHERE rolname LIKE 'regress_passwd_sha_len%'
ORDER BY rolname;
rolname | is_rolpassword_rehashed
-------------------------+-------------------------
- rolname | is_rolpassword_rehashed
--------------------------+-------------------------
- regress_passwd_sha_len0 | f
+ regress_passwd_sha_len0 | t
regress_passwd_sha_len1 | t
regress_passwd_sha_len2 | t
(3 rows)
@@ -135,6 +124,7 @@ DROP ROLE regress_passwd7;
- regress_passwd_sha_len1 | t
- regress_passwd_sha_len2 | t
-(3 rows)
+ rolname | is_rolpassword_rehashed
+---------+-------------------------
+(0 rows)
DROP ROLE regress_passwd1;
DROP ROLE regress_passwd2;
DROP ROLE regress_passwd3;
DROP ROLE regress_passwd4;
DROP ROLE regress_passwd5;
+ERROR: role "regress_passwd5" does not exist
DROP ROLE regress_passwd6;
+ERROR: role "regress_passwd6" does not exist
DROP ROLE regress_passwd7;
+ERROR: role "regress_passwd7" does not exist
DROP ROLE regress_passwd8;
+ERROR: role "regress_passwd8" does not exist
DROP ROLE regress_passwd9;
DROP ROLE regress_passwd_empty;
+ERROR: role "regress_passwd_empty" does not exist
DROP ROLE regress_passwd_sha_len0;
+ERROR: role "regress_passwd_sha_len0" does not exist
DROP ROLE regress_passwd_sha_len1;
+ERROR: role "regress_passwd_sha_len1" does not exist
DROP ROLE regress_passwd_sha_len2;
+ERROR: role "regress_passwd_sha_len2" does not exist
-- all entries should have been removed
SELECT rolname, rolpassword
FROM pg_authid
diff --git a/src/test/regress/expected/privileges.out b/src/test/regress/expected/privileges.out
index 5b9dba7b32..cc408dad42 100644
--- a/src/test/regress/expected/privileges.out
@@ -3173,7 +3194,7 @@ index 1a6c61f49d..1c31ac6a53 100644
-- Test generic object addressing/identification functions
CREATE SCHEMA addr_nsp;
diff --git a/src/test/regress/sql/password.sql b/src/test/regress/sql/password.sql
index 53e86b0b6c..0303fdfe96 100644
index 53e86b0b6c..f07cf1ec54 100644
--- a/src/test/regress/sql/password.sql
+++ b/src/test/regress/sql/password.sql
@@ -10,11 +10,11 @@ SET password_encryption = 'scram-sha-256'; -- ok
@@ -3192,59 +3213,23 @@ index 53e86b0b6c..0303fdfe96 100644
-- check list of created entries
--
@@ -42,26 +42,18 @@ ALTER ROLE regress_passwd2_new RENAME TO regress_passwd2;
@@ -42,14 +42,14 @@ ALTER ROLE regress_passwd2_new RENAME TO regress_passwd2;
SET password_encryption = 'md5';
-- encrypt with MD5
-ALTER ROLE regress_passwd2 PASSWORD 'foo';
--- already encrypted, use as they are
-ALTER ROLE regress_passwd1 PASSWORD 'md5cd3578025fe2c3d7ed1b9a9b26238b70';
-ALTER ROLE regress_passwd3 PASSWORD 'SCRAM-SHA-256$4096:VLK4RMaQLCvNtQ==$6YtlR4t69SguDiwFvbVgVZtuz6gpJQQqUMZ7IQJK5yI=:ps75jrHeYU4lXCcXI4O8oIdJ3eO8o2jirjruw9phBTo=';
+ALTER ROLE regress_passwd2 PASSWORD NEON_PASSWORD_PLACEHOLDER;
-- already encrypted, use as they are
ALTER ROLE regress_passwd1 PASSWORD 'md5cd3578025fe2c3d7ed1b9a9b26238b70';
ALTER ROLE regress_passwd3 PASSWORD 'SCRAM-SHA-256$4096:VLK4RMaQLCvNtQ==$6YtlR4t69SguDiwFvbVgVZtuz6gpJQQqUMZ7IQJK5yI=:ps75jrHeYU4lXCcXI4O8oIdJ3eO8o2jirjruw9phBTo=';
SET password_encryption = 'scram-sha-256';
-- create SCRAM secret
-ALTER ROLE regress_passwd4 PASSWORD 'foo';
--- already encrypted with MD5, use as it is
-CREATE ROLE regress_passwd5 PASSWORD 'md5e73a4b11df52a6068f8b39f90be36023';
+ALTER ROLE regress_passwd4 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+-- Neon does not support encrypted passwords, use unencrypted instead
+CREATE ROLE regress_passwd5 PASSWORD NEON_PASSWORD_PLACEHOLDER;
-- already encrypted with MD5, use as it is
CREATE ROLE regress_passwd5 PASSWORD 'md5e73a4b11df52a6068f8b39f90be36023';
--- This looks like a valid SCRAM-SHA-256 secret, but it is not
--- so it should be hashed with SCRAM-SHA-256.
-CREATE ROLE regress_passwd6 PASSWORD 'SCRAM-SHA-256$1234';
--- These may look like valid MD5 secrets, but they are not, so they
--- should be hashed with SCRAM-SHA-256.
--- trailing garbage at the end
-CREATE ROLE regress_passwd7 PASSWORD 'md5012345678901234567890123456789zz';
--- invalid length
-CREATE ROLE regress_passwd8 PASSWORD 'md501234567890123456789012345678901zz';
+-- Neon does not support encrypted passwords, use unencrypted instead
+CREATE ROLE regress_passwd6 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+CREATE ROLE regress_passwd7 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+CREATE ROLE regress_passwd8 PASSWORD NEON_PASSWORD_PLACEHOLDER;
-- Changing the SCRAM iteration count
SET scram_iterations = 1024;
@@ -78,13 +70,10 @@ ALTER ROLE regress_passwd_empty PASSWORD 'md585939a5ce845f1a1b620742e3c659e0a';
ALTER ROLE regress_passwd_empty PASSWORD 'SCRAM-SHA-256$4096:hpFyHTUsSWcR7O9P$LgZFIt6Oqdo27ZFKbZ2nV+vtnYM995pDh9ca6WSi120=:qVV5NeluNfUPkwm7Vqat25RjSPLkGeoZBQs6wVv+um4=';
SELECT rolpassword FROM pg_authid WHERE rolname='regress_passwd_empty';
--- Test with invalid stored and server keys.
---
--- The first is valid, to act as a control. The others have too long
--- stored/server keys. They will be re-hashed.
-CREATE ROLE regress_passwd_sha_len0 PASSWORD 'SCRAM-SHA-256$4096:A6xHKoH/494E941doaPOYg==$Ky+A30sewHIH3VHQLRN9vYsuzlgNyGNKCh37dy96Rqw=:COPdlNiIkrsacU5QoxydEuOH6e/KfiipeETb/bPw8ZI=';
-CREATE ROLE regress_passwd_sha_len1 PASSWORD 'SCRAM-SHA-256$4096:A6xHKoH/494E941doaPOYg==$Ky+A30sewHIH3VHQLRN9vYsuzlgNyGNKCh37dy96RqwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=:COPdlNiIkrsacU5QoxydEuOH6e/KfiipeETb/bPw8ZI=';
-CREATE ROLE regress_passwd_sha_len2 PASSWORD 'SCRAM-SHA-256$4096:A6xHKoH/494E941doaPOYg==$Ky+A30sewHIH3VHQLRN9vYsuzlgNyGNKCh37dy96Rqw=:COPdlNiIkrsacU5QoxydEuOH6e/KfiipeETb/bPw8ZIAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=';
+-- Neon does not support encrypted passwords, use unencrypted instead
+CREATE ROLE regress_passwd_sha_len0 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+CREATE ROLE regress_passwd_sha_len1 PASSWORD NEON_PASSWORD_PLACEHOLDER;
+CREATE ROLE regress_passwd_sha_len2 PASSWORD NEON_PASSWORD_PLACEHOLDER;
-- Check that the invalid secrets were re-hashed. A re-hashed secret
-- should not contain the original salt.
diff --git a/src/test/regress/sql/privileges.sql b/src/test/regress/sql/privileges.sql
index 249df17a58..b258e7f26a 100644
--- a/src/test/regress/sql/privileges.sql

File diff suppressed because it is too large Load Diff

View File

@@ -7,7 +7,7 @@ license.workspace = true
[features]
default = []
# Enables test specific features.
testing = ["fail/failpoints"]
testing = []
[dependencies]
base64.workspace = true
@@ -19,7 +19,6 @@ camino.workspace = true
chrono.workspace = true
cfg-if.workspace = true
clap.workspace = true
fail.workspace = true
flate2.workspace = true
futures.workspace = true
hyper0 = { workspace = true, features = ["full"] }

View File

@@ -67,16 +67,12 @@ use compute_tools::params::*;
use compute_tools::spec::*;
use compute_tools::swap::resize_swap;
use rlimit::{setrlimit, Resource};
use utils::failpoint_support;
use utils::id::{TenantId, TimelineId};
// this is an arbitrary build tag. Fine as a default / for testing purposes
// in-case of not-set environment var
const BUILD_TAG_DEFAULT: &str = "latest";
fn main() -> Result<()> {
let scenario = failpoint_support::init();
let (build_tag, clap_args) = init()?;
// enable core dumping for all child processes
@@ -88,9 +84,9 @@ fn main() -> Result<()> {
let cli_args = process_cli(&clap_args)?;
// let cli_spec = try_spec_from_cli(&clap_args, &cli_args)?;
let cli_spec = try_spec_from_cli(&clap_args, &cli_args)?;
let wait_spec_result = wait_spec(build_tag, cli_args)?;
let wait_spec_result = wait_spec(build_tag, cli_args, cli_spec)?;
start_postgres(&clap_args, wait_spec_result)?
@@ -104,8 +100,6 @@ fn main() -> Result<()> {
maybe_delay_exit(delay_exit);
scenario.teardown();
deinit_and_exit(wait_pg_result);
}
@@ -252,48 +246,47 @@ fn try_spec_from_cli(
let compute_id = matches.get_one::<String>("compute-id");
let control_plane_uri = matches.get_one::<String>("control-plane-uri");
// First, try to get cluster spec from the cli argument
if let Some(spec_json) = spec_json {
info!("got spec from cli argument {}", spec_json);
return Ok(CliSpecParams {
spec: Some(serde_json::from_str(spec_json)?),
live_config_allowed: false,
});
}
// Second, try to read it from the file if path is provided
if let Some(spec_path) = spec_path {
let file = File::open(Path::new(spec_path))?;
return Ok(CliSpecParams {
spec: Some(serde_json::from_reader(file)?),
live_config_allowed: true,
});
}
let Some(compute_id) = compute_id else {
panic!(
"compute spec should be provided by one of the following ways: \
--spec OR --spec-path OR --control-plane-uri and --compute-id"
);
};
let Some(control_plane_uri) = control_plane_uri else {
panic!("must specify both --control-plane-uri and --compute-id or none");
};
match get_spec_from_control_plane(control_plane_uri, compute_id) {
Ok(spec) => Ok(CliSpecParams {
spec,
live_config_allowed: true,
}),
Err(e) => {
error!(
"cannot get response from control plane: {}\n\
neither spec nor confirmation that compute is in the Empty state was received",
e
);
Err(e)
let spec;
let mut live_config_allowed = false;
match spec_json {
// First, try to get cluster spec from the cli argument
Some(json) => {
info!("got spec from cli argument {}", json);
spec = Some(serde_json::from_str(json)?);
}
}
None => {
// Second, try to read it from the file if path is provided
if let Some(sp) = spec_path {
let path = Path::new(sp);
let file = File::open(path)?;
spec = Some(serde_json::from_reader(file)?);
live_config_allowed = true;
} else if let Some(id) = compute_id {
if let Some(cp_base) = control_plane_uri {
live_config_allowed = true;
spec = match get_spec_from_control_plane(cp_base, id) {
Ok(s) => s,
Err(e) => {
error!("cannot get response from control plane: {}", e);
panic!("neither spec nor confirmation that compute is in the Empty state was received");
}
};
} else {
panic!("must specify both --control-plane-uri and --compute-id or none");
}
} else {
panic!(
"compute spec should be provided by one of the following ways: \
--spec OR --spec-path OR --control-plane-uri and --compute-id"
);
}
}
};
Ok(CliSpecParams {
spec,
live_config_allowed,
})
}
struct CliSpecParams {
@@ -314,41 +307,14 @@ fn wait_spec(
http_port,
..
}: ProcessCliResult,
CliSpecParams {
spec,
live_config_allowed,
}: CliSpecParams,
) -> Result<WaitSpecResult> {
let mut new_state = ComputeState::new();
let spec_set;
let live_config_allowed = true;
let spec = Some(ComputeSpec {
// format_version: todo!(),
// operation_uuid: todo!(),
// features: todo!(),
// swap_size_bytes: todo!(),
// disk_quota_bytes: todo!(),
// disable_lfc_resizing: todo!(),
// cluster: todo!(),
// delta_operations: todo!(),
// skip_pg_catalog_updates: todo!(),
// tenant_id: todo!(),
// timeline_id: todo!(),
// pageserver_connstring: todo!(),
// safekeeper_connstrings: todo!(),
// mode: todo!(),
// storage_auth_token: todo!(),
// remote_extensions: todo!(),
// pgbouncer_settings: todo!(),
// shard_stripe_size: todo!(),
// local_proxy_config: todo!(),
// reconfigure_concurrency: todo!(),
pageserver_connstring: Some("pageserver-1.example.com:5432".to_string()),
safekeeper_connstrings: vec!["safekeeper-1.example.com:5432".to_string()],
tenant_id: Some(TenantId::generate()),
timeline_id: Some(TimelineId::generate()),
..Default::default()
});
if let Some(spec) = spec {
let pspec = ParsedSpec::try_from(spec).map_err(|msg| anyhow::anyhow!(msg))?;
info!("new pspec.spec: {:?}", pspec.spec);
@@ -383,7 +349,9 @@ fn wait_spec(
// available for binding. Prewarming helps Postgres start quicker later,
// because QEMU will already have its memory allocated from the host, and
// the necessary binaries will already be cached.
compute.prewarm_postgres()?;
if !spec_set {
compute.prewarm_postgres()?;
}
// Launch http service first, so that we can serve control-plane requests
// while configuration is still in progress.
@@ -450,14 +418,9 @@ fn start_postgres(
"running compute with features: {:?}",
state.pspec.as_ref().unwrap().spec.features
);
// before we release the mutex, fetch some parameters for later.
let &ComputeSpec {
swap_size_bytes,
disk_quota_bytes,
#[cfg(target_os = "linux")]
disable_lfc_resizing,
..
} = &state.pspec.as_ref().unwrap().spec;
// before we release the mutex, fetch the swap size (if any) for later.
let swap_size_bytes = state.pspec.as_ref().unwrap().spec.swap_size_bytes;
let disk_quota_bytes = state.pspec.as_ref().unwrap().spec.disk_quota_bytes;
drop(state);
// Launch remaining service threads
@@ -562,18 +525,11 @@ fn start_postgres(
// This token is used internally by the monitor to clean up all threads
let token = CancellationToken::new();
// don't pass postgres connection string to vm-monitor if we don't want it to resize LFC
let pgconnstr = if disable_lfc_resizing.unwrap_or(false) {
None
} else {
file_cache_connstr.cloned()
};
let vm_monitor = rt.as_ref().map(|rt| {
rt.spawn(vm_monitor::start(
Box::leak(Box::new(vm_monitor::Args {
cgroup: cgroup.cloned(),
pgconnstr,
pgconnstr: file_cache_connstr.cloned(),
addr: vm_monitor_addr.clone(),
})),
token.clone(),

View File

@@ -34,12 +34,12 @@ use nix::unistd::Pid;
use tracing::{info, info_span, warn, Instrument};
use utils::fs_ext::is_directory_empty;
#[path = "fast_import/aws_s3_sync.rs"]
mod aws_s3_sync;
#[path = "fast_import/child_stdio_to_log.rs"]
mod child_stdio_to_log;
#[path = "fast_import/s3_uri.rs"]
mod s3_uri;
#[path = "fast_import/s5cmd.rs"]
mod s5cmd;
#[derive(clap::Parser)]
struct Args {
@@ -326,7 +326,7 @@ pub(crate) async fn main() -> anyhow::Result<()> {
}
info!("upload pgdata");
aws_s3_sync::sync(Utf8Path::new(&pgdata_dir), &s3_prefix.append("/pgdata/"))
s5cmd::sync(Utf8Path::new(&pgdata_dir), &s3_prefix.append("/"))
.await
.context("sync dump directory to destination")?;
@@ -334,10 +334,10 @@ pub(crate) async fn main() -> anyhow::Result<()> {
{
let status_dir = working_directory.join("status");
std::fs::create_dir(&status_dir).context("create status directory")?;
let status_file = status_dir.join("pgdata");
let status_file = status_dir.join("status");
std::fs::write(&status_file, serde_json::json!({"done": true}).to_string())
.context("write status file")?;
aws_s3_sync::sync(&status_dir, &s3_prefix.append("/status/"))
s5cmd::sync(&status_file, &s3_prefix.append("/status/pgdata"))
.await
.context("sync status directory to destination")?;
}

View File

@@ -4,21 +4,24 @@ use camino::Utf8Path;
use super::s3_uri::S3Uri;
pub(crate) async fn sync(local: &Utf8Path, remote: &S3Uri) -> anyhow::Result<()> {
let mut builder = tokio::process::Command::new("aws");
let mut builder = tokio::process::Command::new("s5cmd");
// s5cmd uses aws-sdk-go v1, hence doesn't support AWS_ENDPOINT_URL
if let Some(val) = std::env::var_os("AWS_ENDPOINT_URL") {
builder.arg("--endpoint-url").arg(val);
}
builder
.arg("s3")
.arg("sync")
.arg(local.as_str())
.arg(remote.to_string());
let st = builder
.spawn()
.context("spawn aws s3 sync")?
.context("spawn s5cmd")?
.wait()
.await
.context("wait for aws s3 sync")?;
.context("wait for s5cmd")?;
if st.success() {
Ok(())
} else {
Err(anyhow::anyhow!("aws s3 sync failed"))
Err(anyhow::anyhow!("s5cmd failed"))
}
}

View File

@@ -15,7 +15,7 @@ use std::time::Instant;
use anyhow::{Context, Result};
use chrono::{DateTime, Utc};
use compute_api::spec::{Database, PgIdent, Role};
use compute_api::spec::{PgIdent, Role};
use futures::future::join_all;
use futures::stream::FuturesUnordered;
use futures::StreamExt;
@@ -45,10 +45,8 @@ use crate::spec_apply::ApplySpecPhase::{
DropInvalidDatabases, DropRoles, HandleNeonExtension, HandleOtherExtensions,
RenameAndDeleteDatabases, RenameRoles, RunInEachDatabase,
};
use crate::spec_apply::PerDatabasePhase;
use crate::spec_apply::PerDatabasePhase::{
ChangeSchemaPerms, DeleteDBRoleReferences, DropSubscriptionsForDeletedDatabases,
HandleAnonExtension,
ChangeSchemaPerms, DeleteDBRoleReferences, HandleAnonExtension,
};
use crate::spec_apply::{apply_operations, MutableApplyContext, DB};
use crate::sync_sk::{check_if_synced, ping_safekeeper};
@@ -358,22 +356,64 @@ impl ComputeNode {
let spec = compute_state.pspec.as_ref().expect("spec must be set");
let start_time = Instant::now();
// Open backup file directly
let backup_file = std::fs::File::open("/var/db/backups/backup.tar.gz")?;
let mut measured_reader = MeasuredReader::new(backup_file);
let shard0_connstr = spec.pageserver_connstr.split(',').next().unwrap();
let mut config = postgres::Config::from_str(shard0_connstr)?;
// Use the storage auth token from the config file, if given.
// Note: this overrides any password set in the connection string.
if let Some(storage_auth_token) = &spec.storage_auth_token {
info!("Got storage auth token from spec file");
config.password(storage_auth_token);
} else {
info!("Storage auth token not set");
}
// Connect to pageserver
let mut client = config.connect(NoTls)?;
let pageserver_connect_micros = start_time.elapsed().as_micros() as u64;
let basebackup_cmd = match lsn {
Lsn(0) => {
if spec.spec.mode != ComputeMode::Primary {
format!(
"basebackup {} {} --gzip --replica",
spec.tenant_id, spec.timeline_id
)
} else {
format!("basebackup {} {} --gzip", spec.tenant_id, spec.timeline_id)
}
}
_ => {
if spec.spec.mode != ComputeMode::Primary {
format!(
"basebackup {} {} {} --gzip --replica",
spec.tenant_id, spec.timeline_id, lsn
)
} else {
format!(
"basebackup {} {} {} --gzip",
spec.tenant_id, spec.timeline_id, lsn
)
}
}
};
let copyreader = client.copy_out(basebackup_cmd.as_str())?;
let mut measured_reader = MeasuredReader::new(copyreader);
let mut bufreader = std::io::BufReader::new(&mut measured_reader);
// Read the archive directly from the file
// Read the archive directly from the `CopyOutReader`
//
// Set `ignore_zeros` so that unpack() reads all the Copy data and
// doesn't stop at the end-of-archive marker.
// doesn't stop at the end-of-archive marker. Otherwise, if the server
// sends an Error after finishing the tarball, we will not notice it.
let mut ar = tar::Archive::new(flate2::read::GzDecoder::new(&mut bufreader));
ar.set_ignore_zeros(true);
ar.unpack(&self.pgdata)?;
// Report metrics
let mut state = self.state.lock().unwrap();
state.metrics.pageserver_connect_micros = 0;
state.metrics.pageserver_connect_micros = pageserver_connect_micros;
state.metrics.basebackup_bytes = measured_reader.get_byte_count() as u64;
state.metrics.basebackup_ms = start_time.elapsed().as_millis() as u64;
Ok(())
@@ -586,7 +626,32 @@ impl ComputeNode {
self.http_port,
)?;
let lsn = Lsn(0);
// Syncing safekeepers is only safe with primary nodes: if a primary
// is already connected it will be kicked out, so a secondary (standby)
// cannot sync safekeepers.
let lsn = match spec.mode {
ComputeMode::Primary => {
info!("checking if safekeepers are synced");
let lsn = if let Ok(Some(lsn)) = self.check_safekeepers_synced(compute_state) {
lsn
} else {
info!("starting safekeepers syncing");
self.sync_safekeepers(pspec.storage_auth_token.clone())
.with_context(|| "failed to sync safekeepers")?
};
info!("safekeepers synced at LSN {}", lsn);
lsn
}
ComputeMode::Static(lsn) => {
info!("Starting read-only node at static LSN {}", lsn);
lsn
}
ComputeMode::Replica => {
info!("Initializing standby from latest Pageserver LSN");
Lsn(0)
}
};
info!(
"getting basebackup@{} from pageserver {}",
lsn, &pspec.pageserver_connstr
@@ -769,7 +834,7 @@ impl ComputeNode {
conf
}
pub async fn get_maintenance_client(
async fn get_maintenance_client(
conf: &tokio_postgres::Config,
) -> Result<tokio_postgres::Client> {
let mut conf = conf.clone();
@@ -878,78 +943,6 @@ impl ComputeNode {
dbs: databases,
}));
// Apply special pre drop database phase.
// NOTE: we use the code of RunInEachDatabase phase for parallelism
// and connection management, but we don't really run it in *each* database,
// only in databases, we're about to drop.
info!("Applying PerDatabase (pre-dropdb) phase");
let concurrency_token = Arc::new(tokio::sync::Semaphore::new(concurrency));
// Run the phase for each database that we're about to drop.
let db_processes = spec
.delta_operations
.iter()
.flatten()
.filter_map(move |op| {
if op.action.as_str() == "delete_db" {
Some(op.name.clone())
} else {
None
}
})
.map(|dbname| {
let spec = spec.clone();
let ctx = ctx.clone();
let jwks_roles = jwks_roles.clone();
let mut conf = conf.as_ref().clone();
let concurrency_token = concurrency_token.clone();
// We only need dbname field for this phase, so set other fields to dummy values
let db = DB::UserDB(Database {
name: dbname.clone(),
owner: "cloud_admin".to_string(),
options: None,
restrict_conn: false,
invalid: false,
});
debug!("Applying per-database phases for Database {:?}", &db);
match &db {
DB::SystemDB => {}
DB::UserDB(db) => {
conf.dbname(db.name.as_str());
}
}
let conf = Arc::new(conf);
let fut = Self::apply_spec_sql_db(
spec.clone(),
conf,
ctx.clone(),
jwks_roles.clone(),
concurrency_token.clone(),
db,
[DropSubscriptionsForDeletedDatabases].to_vec(),
);
Ok(spawn(fut))
})
.collect::<Vec<Result<_, anyhow::Error>>>();
for process in db_processes.into_iter() {
let handle = process?;
if let Err(e) = handle.await? {
// Handle the error case where the database does not exist
// We do not check whether the DB exists or not in the deletion phase,
// so we shouldn't be strict about it in pre-deletion cleanup as well.
if e.to_string().contains("does not exist") {
warn!("Error dropping subscription: {}", e);
} else {
return Err(e);
}
};
}
for phase in [
CreateSuperUser,
DropInvalidDatabases,
@@ -969,7 +962,7 @@ impl ComputeNode {
.await?;
}
info!("Applying RunInEachDatabase2 phase");
info!("Applying RunInEachDatabase phase");
let concurrency_token = Arc::new(tokio::sync::Semaphore::new(concurrency));
let db_processes = spec
@@ -1004,12 +997,6 @@ impl ComputeNode {
jwks_roles.clone(),
concurrency_token.clone(),
db,
[
DeleteDBRoleReferences,
ChangeSchemaPerms,
HandleAnonExtension,
]
.to_vec(),
);
Ok(spawn(fut))
@@ -1056,13 +1043,16 @@ impl ComputeNode {
jwks_roles: Arc<HashSet<String>>,
concurrency_token: Arc<tokio::sync::Semaphore>,
db: DB,
subphases: Vec<PerDatabasePhase>,
) -> Result<()> {
let _permit = concurrency_token.acquire().await?;
let mut client_conn = None;
for subphase in subphases {
for subphase in [
DeleteDBRoleReferences,
ChangeSchemaPerms,
HandleAnonExtension,
] {
apply_operations(
spec.clone(),
ctx.clone(),
@@ -1191,19 +1181,8 @@ impl ComputeNode {
let mut conf = postgres::config::Config::from(conf);
conf.application_name("compute_ctl:migrations");
match conf.connect(NoTls) {
Ok(mut client) => {
if let Err(e) = handle_migrations(&mut client) {
error!("Failed to run migrations: {}", e);
}
}
Err(e) => {
error!(
"Failed to connect to the compute for running migrations: {}",
e
);
}
};
let mut client = conf.connect(NoTls)?;
handle_migrations(&mut client).context("apply_config handle_migrations")
});
Ok::<(), anyhow::Error>(())
@@ -1264,7 +1243,12 @@ impl ComputeNode {
let postgresql_conf_path = pgdata_path.join("postgresql.conf");
config::write_postgres_conf(&postgresql_conf_path, &spec, self.http_port)?;
let max_concurrent_connections = spec.reconfigure_concurrency;
// TODO(ololobus): We need a concurrency during reconfiguration as well,
// but DB is already running and used by user. We can easily get out of
// `max_connections` limit, and the current code won't handle that.
// let compute_state = self.state.lock().unwrap().clone();
// let max_concurrent_connections = self.max_service_connections(&compute_state, &spec);
let max_concurrent_connections = 1;
// Temporarily reset max_cluster_size in config
// to avoid the possibility of hitting the limit, while we are reconfiguring:

View File

@@ -24,11 +24,8 @@ use metrics::proto::MetricFamily;
use metrics::Encoder;
use metrics::TextEncoder;
use tokio::task;
use tokio_util::sync::CancellationToken;
use tracing::{debug, error, info, warn};
use tracing_utils::http::OtelName;
use utils::failpoint_support::failpoints_handler;
use utils::http::error::ApiError;
use utils::http::request::must_get_query_param;
fn status_response_from_state(state: &ComputeState) -> ComputeStatusResponse {
@@ -313,18 +310,6 @@ async fn routes(req: Request<Body>, compute: &Arc<ComputeNode>) -> Response<Body
}
}
(&Method::POST, "/failpoints") if cfg!(feature = "testing") => {
match failpoints_handler(req, CancellationToken::new()).await {
Ok(r) => r,
Err(ApiError::BadRequest(e)) => {
render_json_error(&e.to_string(), StatusCode::BAD_REQUEST)
}
Err(_) => {
render_json_error("Internal server error", StatusCode::INTERNAL_SERVER_ERROR)
}
}
}
// download extension files from remote extension storage on demand
(&Method::POST, route) if route.starts_with("/extension_server/") => {
info!("serving {:?} POST request", route);

View File

@@ -537,14 +537,12 @@ components:
properties:
extname:
type: string
version:
type: string
versions:
type: array
items:
type: string
n_databases:
type: integer
owned_by_superuser:
type: integer
SetRoleGrantsRequest:
type: object

View File

@@ -1,6 +1,7 @@
use compute_api::responses::{InstalledExtension, InstalledExtensions};
use metrics::proto::MetricFamily;
use std::collections::HashMap;
use std::collections::HashSet;
use anyhow::Result;
use postgres::{Client, NoTls};
@@ -37,77 +38,61 @@ fn list_dbs(client: &mut Client) -> Result<Vec<String>> {
/// Connect to every database (see list_dbs above) and get the list of installed extensions.
///
/// Same extension can be installed in multiple databases with different versions,
/// so we report a separate metric (number of databases where it is installed)
/// for each extension version.
/// we only keep the highest and lowest version across all databases.
pub fn get_installed_extensions(mut conf: postgres::config::Config) -> Result<InstalledExtensions> {
conf.application_name("compute_ctl:get_installed_extensions");
let mut client = conf.connect(NoTls)?;
let databases: Vec<String> = list_dbs(&mut client)?;
let mut extensions_map: HashMap<(String, String, String), InstalledExtension> = HashMap::new();
let mut extensions_map: HashMap<String, InstalledExtension> = HashMap::new();
for db in databases.iter() {
conf.dbname(db);
let mut db_client = conf.connect(NoTls)?;
let extensions: Vec<(String, String, i32)> = db_client
let extensions: Vec<(String, String)> = db_client
.query(
"SELECT extname, extversion, extowner::integer FROM pg_catalog.pg_extension",
"SELECT extname, extversion FROM pg_catalog.pg_extension;",
&[],
)?
.iter()
.map(|row| {
(
row.get("extname"),
row.get("extversion"),
row.get("extowner"),
)
})
.map(|row| (row.get("extname"), row.get("extversion")))
.collect();
for (extname, v, extowner) in extensions.iter() {
for (extname, v) in extensions.iter() {
let version = v.to_string();
// check if the extension is owned by superuser
// 10 is the oid of superuser
let owned_by_superuser = if *extowner == 10 { "1" } else { "0" };
// increment the number of databases where the version of extension is installed
INSTALLED_EXTENSIONS
.with_label_values(&[extname, &version])
.inc();
extensions_map
.entry((
extname.to_string(),
version.clone(),
owned_by_superuser.to_string(),
))
.entry(extname.to_string())
.and_modify(|e| {
e.versions.insert(version.clone());
// count the number of databases where the extension is installed
e.n_databases += 1;
})
.or_insert(InstalledExtension {
extname: extname.to_string(),
version: version.clone(),
versions: HashSet::from([version.clone()]),
n_databases: 1,
owned_by_superuser: owned_by_superuser.to_string(),
});
}
}
for (key, ext) in extensions_map.iter() {
let (extname, version, owned_by_superuser) = key;
let n_databases = ext.n_databases as u64;
INSTALLED_EXTENSIONS
.with_label_values(&[extname, version, owned_by_superuser])
.set(n_databases);
}
Ok(InstalledExtensions {
let res = InstalledExtensions {
extensions: extensions_map.into_values().collect(),
})
};
Ok(res)
}
static INSTALLED_EXTENSIONS: Lazy<UIntGaugeVec> = Lazy::new(|| {
register_uint_gauge_vec!(
"compute_installed_extensions",
"Number of databases where the version of extension is installed",
&["extension_name", "version", "owned_by_superuser"]
&["extension_name", "version"]
)
.expect("failed to define a metric")
});

View File

@@ -1,16 +1,13 @@
use anyhow::{Context, Result};
use fail::fail_point;
use postgres::{Client, Transaction};
use postgres::Client;
use tracing::info;
/// Runs a series of migrations on a target database
pub(crate) struct MigrationRunner<'m> {
client: &'m mut Client,
migrations: &'m [&'m str],
}
impl<'m> MigrationRunner<'m> {
/// Create a new migration runner
pub fn new(client: &'m mut Client, migrations: &'m [&'m str]) -> Self {
// The neon_migration.migration_id::id column is a bigint, which is equivalent to an i64
assert!(migrations.len() + 1 < i64::MAX as usize);
@@ -18,110 +15,87 @@ impl<'m> MigrationRunner<'m> {
Self { client, migrations }
}
/// Get the current value neon_migration.migration_id
fn get_migration_id(&mut self) -> Result<i64> {
let query = "SELECT id FROM neon_migration.migration_id";
let row = self
.client
.query_one("SELECT id FROM neon_migration.migration_id", &[])?;
.query_one(query, &[])
.context("run_migrations get migration_id")?;
Ok(row.get::<&str, i64>("id"))
}
/// Update the neon_migration.migration_id value
///
/// This function has a fail point called compute-migration, which can be
/// used if you would like to fail the application of a series of migrations
/// at some point.
fn update_migration_id(txn: &mut Transaction, migration_id: i64) -> Result<()> {
// We use this fail point in order to check that failing in the
// middle of applying a series of migrations fails in an expected
// manner
if cfg!(feature = "testing") {
let fail = (|| {
fail_point!("compute-migration", |fail_migration_id| {
migration_id == fail_migration_id.unwrap().parse::<i64>().unwrap()
});
fn update_migration_id(&mut self, migration_id: i64) -> Result<()> {
let setval = format!("UPDATE neon_migration.migration_id SET id={}", migration_id);
false
})();
if fail {
return Err(anyhow::anyhow!(format!(
"migration {} was configured to fail because of a failpoint",
migration_id
)));
}
}
txn.query(
"UPDATE neon_migration.migration_id SET id = $1",
&[&migration_id],
)
.with_context(|| format!("update neon_migration.migration_id to {migration_id}"))?;
self.client
.simple_query(&setval)
.context("run_migrations update id")?;
Ok(())
}
/// Prepare the migrations the target database for handling migrations
fn prepare_database(&mut self) -> Result<()> {
self.client
.simple_query("CREATE SCHEMA IF NOT EXISTS neon_migration")?;
self.client.simple_query("CREATE TABLE IF NOT EXISTS neon_migration.migration_id (key INT NOT NULL PRIMARY KEY, id bigint NOT NULL DEFAULT 0)")?;
self.client.simple_query(
"INSERT INTO neon_migration.migration_id VALUES (0, 0) ON CONFLICT DO NOTHING",
)?;
self.client
.simple_query("ALTER SCHEMA neon_migration OWNER TO cloud_admin")?;
self.client
.simple_query("REVOKE ALL ON SCHEMA neon_migration FROM PUBLIC")?;
fn prepare_migrations(&mut self) -> Result<()> {
let query = "CREATE SCHEMA IF NOT EXISTS neon_migration";
self.client.simple_query(query)?;
let query = "CREATE TABLE IF NOT EXISTS neon_migration.migration_id (key INT NOT NULL PRIMARY KEY, id bigint NOT NULL DEFAULT 0)";
self.client.simple_query(query)?;
let query = "INSERT INTO neon_migration.migration_id VALUES (0, 0) ON CONFLICT DO NOTHING";
self.client.simple_query(query)?;
let query = "ALTER SCHEMA neon_migration OWNER TO cloud_admin";
self.client.simple_query(query)?;
let query = "REVOKE ALL ON SCHEMA neon_migration FROM PUBLIC";
self.client.simple_query(query)?;
Ok(())
}
/// Run an individual migration
fn run_migration(txn: &mut Transaction, migration_id: i64, migration: &str) -> Result<()> {
if migration.starts_with("-- SKIP") {
info!("Skipping migration id={}", migration_id);
// Even though we are skipping the migration, updating the
// migration ID should help keep logic easy to understand when
// trying to understand the state of a cluster.
Self::update_migration_id(txn, migration_id)?;
} else {
info!("Running migration id={}:\n{}\n", migration_id, migration);
txn.simple_query(migration)
.with_context(|| format!("apply migration {migration_id}"))?;
Self::update_migration_id(txn, migration_id)?;
}
Ok(())
}
/// Run the configured set of migrations
pub fn run_migrations(mut self) -> Result<()> {
self.prepare_database()
.context("prepare database to handle migrations")?;
self.prepare_migrations()?;
let mut current_migration = self.get_migration_id()? as usize;
while current_migration < self.migrations.len() {
// The index lags the migration ID by 1, so the current migration
// ID is also the next index
let migration_id = (current_migration + 1) as i64;
macro_rules! migration_id {
($cm:expr) => {
($cm + 1) as i64
};
}
let mut txn = self
.client
.transaction()
.with_context(|| format!("begin transaction for migration {migration_id}"))?;
let migration = self.migrations[current_migration];
Self::run_migration(&mut txn, migration_id, self.migrations[current_migration])
.with_context(|| format!("running migration {migration_id}"))?;
if migration.starts_with("-- SKIP") {
info!("Skipping migration id={}", migration_id!(current_migration));
} else {
info!(
"Running migration id={}:\n{}\n",
migration_id!(current_migration),
migration
);
txn.commit()
.with_context(|| format!("commit transaction for migration {migration_id}"))?;
self.client
.simple_query("BEGIN")
.context("begin migration")?;
info!("Finished migration id={}", migration_id);
self.client.simple_query(migration).with_context(|| {
format!(
"run_migrations migration id={}",
migration_id!(current_migration)
)
})?;
// Migration IDs start at 1
self.update_migration_id(migration_id!(current_migration))?;
self.client
.simple_query("COMMIT")
.context("commit migration")?;
info!("Finished migration id={}", migration_id!(current_migration));
}
current_migration += 1;
}

View File

@@ -1,9 +0,0 @@
DO $$
DECLARE
bypassrls boolean;
BEGIN
SELECT rolbypassrls INTO bypassrls FROM pg_roles WHERE rolname = 'neon_superuser';
IF NOT bypassrls THEN
RAISE EXCEPTION 'neon_superuser cannot bypass RLS';
END IF;
END $$;

View File

@@ -1,25 +0,0 @@
DO $$
DECLARE
role record;
BEGIN
FOR role IN
SELECT rolname AS name, rolinherit AS inherit
FROM pg_roles
WHERE pg_has_role(rolname, 'neon_superuser', 'member')
LOOP
IF NOT role.inherit THEN
RAISE EXCEPTION '% cannot inherit', quote_ident(role.name);
END IF;
END LOOP;
FOR role IN
SELECT rolname AS name, rolbypassrls AS bypassrls
FROM pg_roles
WHERE NOT pg_has_role(rolname, 'neon_superuser', 'member')
AND NOT starts_with(rolname, 'pg_')
LOOP
IF role.bypassrls THEN
RAISE EXCEPTION '% can bypass RLS', quote_ident(role.name);
END IF;
END LOOP;
END $$;

View File

@@ -1,10 +0,0 @@
DO $$
BEGIN
IF (SELECT current_setting('server_version_num')::numeric < 160000) THEN
RETURN;
END IF;
IF NOT (SELECT pg_has_role('neon_superuser', 'pg_create_subscription', 'member')) THEN
RAISE EXCEPTION 'neon_superuser cannot execute pg_create_subscription';
END IF;
END $$;

View File

@@ -1,19 +0,0 @@
DO $$
DECLARE
monitor record;
BEGIN
SELECT pg_has_role('neon_superuser', 'pg_monitor', 'member') AS member,
admin_option AS admin
INTO monitor
FROM pg_auth_members
WHERE roleid = 'pg_monitor'::regrole
AND member = 'pg_monitor'::regrole;
IF NOT monitor.member THEN
RAISE EXCEPTION 'neon_superuser is not a member of pg_monitor';
END IF;
IF NOT monitor.admin THEN
RAISE EXCEPTION 'neon_superuser cannot grant pg_monitor';
END IF;
END $$;

View File

@@ -1,2 +0,0 @@
-- This test was never written becuase at the time migration tests were added
-- the accompanying migration was already skipped.

View File

@@ -1,2 +0,0 @@
-- This test was never written becuase at the time migration tests were added
-- the accompanying migration was already skipped.

View File

@@ -1,2 +0,0 @@
-- This test was never written becuase at the time migration tests were added
-- the accompanying migration was already skipped.

View File

@@ -1,2 +0,0 @@
-- This test was never written becuase at the time migration tests were added
-- the accompanying migration was already skipped.

View File

@@ -1,2 +0,0 @@
-- This test was never written becuase at the time migration tests were added
-- the accompanying migration was already skipped.

View File

@@ -1,13 +0,0 @@
DO $$
DECLARE
can_execute boolean;
BEGIN
SELECT bool_and(has_function_privilege('neon_superuser', oid, 'execute'))
INTO can_execute
FROM pg_proc
WHERE proname IN ('pg_export_snapshot', 'pg_log_standby_snapshot')
AND pronamespace = 'pg_catalog'::regnamespace;
IF NOT can_execute THEN
RAISE EXCEPTION 'neon_superuser cannot execute both pg_export_snapshot and pg_log_standby_snapshot';
END IF;
END $$;

View File

@@ -1,13 +0,0 @@
DO $$
DECLARE
can_execute boolean;
BEGIN
SELECT has_function_privilege('neon_superuser', oid, 'execute')
INTO can_execute
FROM pg_proc
WHERE proname = 'pg_show_replication_origin_status'
AND pronamespace = 'pg_catalog'::regnamespace;
IF NOT can_execute THEN
RAISE EXCEPTION 'neon_superuser cannot execute pg_show_replication_origin_status';
END IF;
END $$;

View File

@@ -47,7 +47,6 @@ pub enum PerDatabasePhase {
DeleteDBRoleReferences,
ChangeSchemaPerms,
HandleAnonExtension,
DropSubscriptionsForDeletedDatabases,
}
#[derive(Clone, Debug)]
@@ -327,12 +326,13 @@ async fn get_operations<'a>(
// Use FORCE to drop database even if there are active connections.
// We run this from `cloud_admin`, so it should have enough privileges.
//
// NB: there could be other db states, which prevent us from dropping
// the database. For example, if db is used by any active subscription
// or replication slot.
// Such cases are handled in the DropSubscriptionsForDeletedDatabases
// phase. We do all the cleanup before actually dropping the database.
// TODO: deal with it once we allow logical replication. Proper fix should
// involve returning an error code to the control plane, so it could
// figure out that this is a non-retryable error, return it to the user
// and fail operation permanently.
let drop_db_query: String = format!(
"DROP DATABASE IF EXISTS {} WITH (FORCE)",
&op.name.pg_quote()
@@ -444,30 +444,6 @@ async fn get_operations<'a>(
}
ApplySpecPhase::RunInEachDatabase { db, subphase } => {
match subphase {
PerDatabasePhase::DropSubscriptionsForDeletedDatabases => {
match &db {
DB::UserDB(db) => {
let drop_subscription_query: String = format!(
include_str!("sql/drop_subscription_for_drop_dbs.sql"),
datname_str = escape_literal(&db.name),
);
let operations = vec![Operation {
query: drop_subscription_query,
comment: Some(format!(
"optionally dropping subscriptions for DB {}",
db.name,
)),
}]
.into_iter();
Ok(Box::new(operations))
}
// skip this cleanup for the system databases
// because users can't drop them
DB::SystemDB => Ok(Box::new(empty())),
}
}
PerDatabasePhase::DeleteDBRoleReferences => {
let ctx = ctx.read().await;

View File

@@ -1,11 +0,0 @@
DO $$
DECLARE
subname TEXT;
BEGIN
FOR subname IN SELECT pg_subscription.subname FROM pg_subscription WHERE subdbid = (SELECT oid FROM pg_database WHERE datname = {datname_str}) LOOP
EXECUTE format('ALTER SUBSCRIPTION %I DISABLE;', subname);
EXECUTE format('ALTER SUBSCRIPTION %I SET (slot_name = NONE);', subname);
EXECUTE format('DROP SUBSCRIPTION %I;', subname);
END LOOP;
END;
$$;

View File

@@ -274,7 +274,6 @@ fn fill_remote_storage_secrets_vars(mut cmd: &mut Command) -> &mut Command {
for env_key in [
"AWS_ACCESS_KEY_ID",
"AWS_SECRET_ACCESS_KEY",
"AWS_SESSION_TOKEN",
"AWS_PROFILE",
// HOME is needed in combination with `AWS_PROFILE` to pick up the SSO sessions.
"HOME",

View File

@@ -19,7 +19,6 @@ use control_plane::storage_controller::{
NeonStorageControllerStartArgs, NeonStorageControllerStopArgs, StorageController,
};
use control_plane::{broker, local_env};
use nix::fcntl::{flock, FlockArg};
use pageserver_api::config::{
DEFAULT_HTTP_LISTEN_PORT as DEFAULT_PAGESERVER_HTTP_PORT,
DEFAULT_PG_LISTEN_PORT as DEFAULT_PAGESERVER_PG_PORT,
@@ -37,8 +36,6 @@ use safekeeper_api::{
};
use std::borrow::Cow;
use std::collections::{BTreeSet, HashMap};
use std::fs::File;
use std::os::fd::AsRawFd;
use std::path::PathBuf;
use std::process::exit;
use std::str::FromStr;
@@ -692,21 +689,6 @@ struct TimelineTreeEl {
pub children: BTreeSet<TimelineId>,
}
/// A flock-based guard over the neon_local repository directory
struct RepoLock {
_file: File,
}
impl RepoLock {
fn new() -> Result<Self> {
let repo_dir = File::open(local_env::base_path())?;
let repo_dir_fd = repo_dir.as_raw_fd();
flock(repo_dir_fd, FlockArg::LockExclusive)?;
Ok(Self { _file: repo_dir })
}
}
// Main entry point for the 'neon_local' CLI utility
//
// This utility helps to manage neon installation. That includes following:
@@ -718,14 +700,9 @@ fn main() -> Result<()> {
let cli = Cli::parse();
// Check for 'neon init' command first.
let (subcommand_result, _lock) = if let NeonLocalCmd::Init(args) = cli.command {
(handle_init(&args).map(|env| Some(Cow::Owned(env))), None)
let subcommand_result = if let NeonLocalCmd::Init(args) = cli.command {
handle_init(&args).map(|env| Some(Cow::Owned(env)))
} else {
// This tool uses a collection of simple files to store its state, and consequently
// it is not generally safe to run multiple commands concurrently. Rather than expect
// all callers to know this, use a lock file to protect against concurrent execution.
let _repo_lock = RepoLock::new().unwrap();
// all other commands need an existing config
let env = LocalEnv::load_config(&local_env::base_path()).context("Error loading config")?;
let original_env = env.clone();
@@ -751,12 +728,11 @@ fn main() -> Result<()> {
NeonLocalCmd::Mappings(subcmd) => handle_mappings(&subcmd, env),
};
let subcommand_result = if &original_env != env {
if &original_env != env {
subcommand_result.map(|()| Some(Cow::Borrowed(env)))
} else {
subcommand_result.map(|()| None)
};
(subcommand_result, Some(_repo_lock))
}
};
match subcommand_result {
@@ -946,7 +922,7 @@ fn handle_init(args: &InitCmdArgs) -> anyhow::Result<LocalEnv> {
} else {
// User (likely interactive) did not provide a description of the environment, give them the default
NeonLocalInitConf {
control_plane_api: Some(DEFAULT_PAGESERVER_CONTROL_PLANE_API.parse().unwrap()),
control_plane_api: Some(Some(DEFAULT_PAGESERVER_CONTROL_PLANE_API.parse().unwrap())),
broker: NeonBroker {
listen_addr: DEFAULT_BROKER_ADDR.parse().unwrap(),
},
@@ -1742,15 +1718,18 @@ async fn handle_start_all_impl(
broker::start_broker_process(env, &retry_timeout).await
});
js.spawn(async move {
let storage_controller = StorageController::from_env(env);
storage_controller
.start(NeonStorageControllerStartArgs::with_default_instance_id(
retry_timeout,
))
.await
.map_err(|e| e.context("start storage_controller"))
});
// Only start the storage controller if the pageserver is configured to need it
if env.control_plane_api.is_some() {
js.spawn(async move {
let storage_controller = StorageController::from_env(env);
storage_controller
.start(NeonStorageControllerStartArgs::with_default_instance_id(
retry_timeout,
))
.await
.map_err(|e| e.context("start storage_controller"))
});
}
for ps_conf in &env.pageservers {
js.spawn(async move {
@@ -1795,6 +1774,10 @@ async fn neon_start_status_check(
const RETRY_INTERVAL: Duration = Duration::from_millis(100);
const NOTICE_AFTER_RETRIES: Duration = Duration::from_secs(5);
if env.control_plane_api.is_none() {
return Ok(());
}
let storcon = StorageController::from_env(env);
let retries = retry_timeout.as_millis() / RETRY_INTERVAL.as_millis();

View File

@@ -53,7 +53,6 @@ use compute_api::spec::Role;
use nix::sys::signal::kill;
use nix::sys::signal::Signal;
use pageserver_api::shard::ShardStripeSize;
use reqwest::header::CONTENT_TYPE;
use serde::{Deserialize, Serialize};
use url::Host;
use utils::id::{NodeId, TenantId, TimelineId};
@@ -316,10 +315,6 @@ impl Endpoint {
// and can cause errors like 'no unpinned buffers available', see
// <https://github.com/neondatabase/neon/issues/9956>
conf.append("shared_buffers", "1MB");
// Postgres defaults to effective_io_concurrency=1, which does not exercise the pageserver's
// batching logic. Set this to 2 so that we exercise the code a bit without letting
// individual tests do a lot of concurrent work on underpowered test machines
conf.append("effective_io_concurrency", "2");
conf.append("fsync", "off");
conf.append("max_connections", "100");
conf.append("wal_level", "logical");
@@ -585,7 +580,6 @@ impl Endpoint {
features: self.features.clone(),
swap_size_bytes: None,
disk_quota_bytes: None,
disable_lfc_resizing: None,
cluster: Cluster {
cluster_id: None, // project ID: not used
name: None, // project name: not used
@@ -624,7 +618,6 @@ impl Endpoint {
pgbouncer_settings: None,
shard_stripe_size: Some(shard_stripe_size),
local_proxy_config: None,
reconfigure_concurrency: 1,
};
let spec_path = self.endpoint_path().join("spec.json");
std::fs::write(spec_path, serde_json::to_string_pretty(&spec)?)?;
@@ -815,7 +808,7 @@ impl Endpoint {
}
let client = reqwest::Client::builder()
.timeout(Duration::from_secs(120))
.timeout(Duration::from_secs(30))
.build()
.unwrap();
let response = client
@@ -824,7 +817,6 @@ impl Endpoint {
self.http_address.ip(),
self.http_address.port()
))
.header(CONTENT_TYPE.as_str(), "application/json")
.body(format!(
"{{\"spec\":{}}}",
serde_json::to_string_pretty(&spec)?

View File

@@ -76,7 +76,7 @@ pub struct LocalEnv {
// Control plane upcall API for pageserver: if None, we will not run storage_controller If set, this will
// be propagated into each pageserver's configuration.
pub control_plane_api: Url,
pub control_plane_api: Option<Url>,
// Control plane upcall API for storage controller. If set, this will be propagated into the
// storage controller's configuration.
@@ -133,7 +133,7 @@ pub struct NeonLocalInitConf {
pub storage_controller: Option<NeonStorageControllerConf>,
pub pageservers: Vec<NeonLocalInitPageserverConf>,
pub safekeepers: Vec<SafekeeperConf>,
pub control_plane_api: Option<Url>,
pub control_plane_api: Option<Option<Url>>,
pub control_plane_compute_hook_api: Option<Option<Url>>,
}
@@ -180,7 +180,7 @@ impl NeonStorageControllerConf {
const DEFAULT_MAX_WARMING_UP_INTERVAL: std::time::Duration = std::time::Duration::from_secs(30);
// Very tight heartbeat interval to speed up tests
const DEFAULT_HEARTBEAT_INTERVAL: std::time::Duration = std::time::Duration::from_millis(1000);
const DEFAULT_HEARTBEAT_INTERVAL: std::time::Duration = std::time::Duration::from_millis(100);
}
impl Default for NeonStorageControllerConf {
@@ -535,7 +535,7 @@ impl LocalEnv {
storage_controller,
pageservers,
safekeepers,
control_plane_api: control_plane_api.unwrap(),
control_plane_api,
control_plane_compute_hook_api,
branch_name_mappings,
}
@@ -638,7 +638,7 @@ impl LocalEnv {
storage_controller: self.storage_controller.clone(),
pageservers: vec![], // it's skip_serializing anyway
safekeepers: self.safekeepers.clone(),
control_plane_api: Some(self.control_plane_api.clone()),
control_plane_api: self.control_plane_api.clone(),
control_plane_compute_hook_api: self.control_plane_compute_hook_api.clone(),
branch_name_mappings: self.branch_name_mappings.clone(),
},
@@ -768,7 +768,7 @@ impl LocalEnv {
storage_controller: storage_controller.unwrap_or_default(),
pageservers: pageservers.iter().map(Into::into).collect(),
safekeepers,
control_plane_api: control_plane_api.unwrap(),
control_plane_api: control_plane_api.unwrap_or_default(),
control_plane_compute_hook_api: control_plane_compute_hook_api.unwrap_or_default(),
branch_name_mappings: Default::default(),
};

View File

@@ -95,19 +95,21 @@ impl PageServerNode {
let mut overrides = vec![pg_distrib_dir_param, broker_endpoint_param];
overrides.push(format!(
"control_plane_api='{}'",
self.env.control_plane_api.as_str()
));
if let Some(control_plane_api) = &self.env.control_plane_api {
overrides.push(format!(
"control_plane_api='{}'",
control_plane_api.as_str()
));
// Storage controller uses the same auth as pageserver: if JWT is enabled
// for us, we will also need it to talk to them.
if matches!(conf.http_auth_type, AuthType::NeonJWT) {
let jwt_token = self
.env
.generate_auth_token(&Claims::new(None, Scope::GenerationsApi))
.unwrap();
overrides.push(format!("control_plane_api_token='{}'", jwt_token));
// Storage controller uses the same auth as pageserver: if JWT is enabled
// for us, we will also need it to talk to them.
if matches!(conf.http_auth_type, AuthType::NeonJWT) {
let jwt_token = self
.env
.generate_auth_token(&Claims::new(None, Scope::GenerationsApi))
.unwrap();
overrides.push(format!("control_plane_api_token='{}'", jwt_token));
}
}
if !conf.other.contains_key("remote_storage") {
@@ -433,7 +435,7 @@ impl PageServerNode {
) -> anyhow::Result<()> {
let config = Self::parse_config(settings)?;
self.http_client
.set_tenant_config(&models::TenantConfigRequest { tenant_id, config })
.tenant_config(&models::TenantConfigRequest { tenant_id, config })
.await?;
Ok(())

View File

@@ -338,7 +338,7 @@ impl StorageController {
.port(),
)
} else {
let listen_url = self.env.control_plane_api.clone();
let listen_url = self.env.control_plane_api.clone().unwrap();
let listen = format!(
"{}:{}",
@@ -708,7 +708,7 @@ impl StorageController {
} else {
// The configured URL has the /upcall path prefix for pageservers to use: we will strip that out
// for general purpose API access.
let listen_url = self.env.control_plane_api.clone();
let listen_url = self.env.control_plane_api.clone().unwrap();
Url::from_str(&format!(
"http://{}:{}/{path}",
listen_url.host_str().unwrap(),

View File

@@ -5,13 +5,12 @@ use clap::{Parser, Subcommand};
use pageserver_api::{
controller_api::{
AvailabilityZone, NodeAvailabilityWrapper, NodeDescribeResponse, NodeShardResponse,
SafekeeperDescribeResponse, ShardSchedulingPolicy, TenantCreateRequest,
TenantDescribeResponse, TenantPolicyRequest,
ShardSchedulingPolicy, TenantCreateRequest, TenantDescribeResponse, TenantPolicyRequest,
},
models::{
EvictionPolicy, EvictionPolicyLayerAccessThreshold, LocationConfigSecondary,
ShardParameters, TenantConfig, TenantConfigPatchRequest, TenantConfigRequest,
TenantShardSplitRequest, TenantShardSplitResponse,
ShardParameters, TenantConfig, TenantConfigRequest, TenantShardSplitRequest,
TenantShardSplitResponse,
},
shard::{ShardStripeSize, TenantShardId},
};
@@ -117,19 +116,9 @@ enum Command {
#[arg(long)]
tenant_shard_id: TenantShardId,
},
/// Set the pageserver tenant configuration of a tenant: this is the configuration structure
/// Modify the pageserver tenant configuration of a tenant: this is the configuration structure
/// that is passed through to pageservers, and does not affect storage controller behavior.
/// Any previous tenant configs are overwritten.
SetTenantConfig {
#[arg(long)]
tenant_id: TenantId,
#[arg(long)]
config: String,
},
/// Patch the pageserver tenant configuration of a tenant. Any fields with null values in the
/// provided JSON are unset from the tenant config and all fields with non-null values are set.
/// Unspecified fields are not changed.
PatchTenantConfig {
TenantConfig {
#[arg(long)]
tenant_id: TenantId,
#[arg(long)]
@@ -212,8 +201,6 @@ enum Command {
#[arg(long)]
timeout: humantime::Duration,
},
/// List safekeepers known to the storage controller
Safekeepers {},
}
#[derive(Parser)]
@@ -562,21 +549,11 @@ async fn main() -> anyhow::Result<()> {
)
.await?;
}
Command::SetTenantConfig { tenant_id, config } => {
Command::TenantConfig { tenant_id, config } => {
let tenant_conf = serde_json::from_str(&config)?;
vps_client
.set_tenant_config(&TenantConfigRequest {
tenant_id,
config: tenant_conf,
})
.await?;
}
Command::PatchTenantConfig { tenant_id, config } => {
let tenant_conf = serde_json::from_str(&config)?;
vps_client
.patch_tenant_config(&TenantConfigPatchRequest {
.tenant_config(&TenantConfigRequest {
tenant_id,
config: tenant_conf,
})
@@ -759,7 +736,7 @@ async fn main() -> anyhow::Result<()> {
threshold,
} => {
vps_client
.set_tenant_config(&TenantConfigRequest {
.tenant_config(&TenantConfigRequest {
tenant_id,
config: TenantConfig {
eviction_policy: Some(EvictionPolicy::LayerAccessThreshold(
@@ -1023,31 +1000,6 @@ async fn main() -> anyhow::Result<()> {
"Fill was cancelled for node {node_id}. Schedulling policy is now {final_policy:?}"
);
}
Command::Safekeepers {} => {
let mut resp = storcon_client
.dispatch::<(), Vec<SafekeeperDescribeResponse>>(
Method::GET,
"control/v1/safekeeper".to_string(),
None,
)
.await?;
resp.sort_by(|a, b| a.id.cmp(&b.id));
let mut table = comfy_table::Table::new();
table.set_header(["Id", "Version", "Host", "Port", "Http Port", "AZ Id"]);
for sk in resp {
table.add_row([
format!("{}", sk.id),
format!("{}", sk.version),
sk.host,
format!("{}", sk.port),
format!("{}", sk.http_port),
sk.availability_zone_id.to_string(),
]);
}
println!("{table}");
}
}
Ok(())

View File

@@ -1 +0,0 @@
backup.tar.gz

View File

@@ -1,21 +0,0 @@
To build a compute image:
```
docker build --build-arg GIT_VERSION=custombuild --build-arg PG_VERSION=v16 -t neon-local-v16 -f ../compute/compute-node.Dockerfile .. && \
../../autoscaling/bin/vm-builder \
-spec=../compute/vm-image-spec-bullseye.yaml \
-src=neon-local-v16:latest \
-dst=vm-neon-local-v16:latest \
-target-arch=linux/amd64 \
-size 2G && \
../../autoscaling/bin/kind load docker-image vm-neon-local-v16:latest --name neonvm-arthur
```
To start a compute node:
```
kubectl apply -f ./spec.yml
```
How to destroy:
```
kubectl delete -f ./spec.yml
```

View File

@@ -1,99 +0,0 @@
apiVersion: vm.neon.tech/v1
kind: VirtualMachine
metadata:
annotations:
autoscaling.neon.tech/bounds: '{"min":{"cpu":"250m","mem":"1Gi"},"max":{"cpu":"2","mem":"8Gi"}}'
autoscaling.neon.tech/config: '{"enableLFCMetrics":true}'
creationTimestamp: "2025-01-04T18:37:29Z"
finalizers:
- vm.neon.tech/finalizer
generation: 1
labels:
autoscaling.neon.tech/enabled: "true"
neon/component: compute-node
neon/compute-id: compute-purple-art-unreal
neon/endpoint-id: ep-unreal
name: compute-purple-art-unreal
namespace: default
spec:
cpuScalingMode: QmpScaling
disks:
- emptyDisk:
discard: true
size: 36096Mi
mountPath: /neonvm/cache
name: cache
readOnly: false
- emptyDisk:
discard: true
enableQuotas: true
size: 150Gi
mountPath: /var/db/postgres/compute
name: pgdata
readOnly: false
enableAcceleration: true
enableNetworkMonitoring: false
enableSSH: true
guest:
args:
- -c
- /usr/local/bin/compute_ctl -D /var/db/postgres/compute/pgdata -b /usr/local/bin/postgres
-C postgresql://cloud_admin@127.0.0.1/postgres?options=-c%20default_transaction_read_only%3Dfalse
--compute-id compute-purple-art-unreal --control-plane-uri http://dontexist.local:9096
--resize-swap-on-bind --set-disk-quota-for-fs /var/db/postgres/compute 2>&1
command:
- /bin/sh
cpus:
max: 10
min: 250m
use: 500m
env:
- name: RUST_LOG
value: info
- name: OTEL_SDK_DISABLED
value: "true"
- name: AUTOSCALING
value: "true"
memorySlotSize: 1Gi
memorySlots:
max: 40
min: 1
use: 2
ports:
- name: postgres
port: 5432
protocol: TCP
- name: control
port: 3080
protocol: TCP
- name: pooler
port: 6432
protocol: TCP
- name: host-metrics
port: 9100
protocol: TCP
- name: metrics
port: 9187
protocol: TCP
- name: sql-exporter
port: 9399
protocol: TCP
- name: sql-exporter-2
port: 9499
protocol: TCP
- name: vm-monitor
port: 10301
protocol: TCP
- name: local-proxy
port: 10432
protocol: TCP
rootDisk:
image: vm-neon-local-v16
imagePullPolicy: IfNotPresent
size: 20Gi
settings:
swap: 40Gi
sysctl:
- vm.overcommit_memory=2
restartPolicy: Always
schedulerName: autoscale-scheduler

View File

@@ -42,7 +42,6 @@ allow = [
"MPL-2.0",
"OpenSSL",
"Unicode-DFS-2016",
"Unicode-3.0",
]
confidence-threshold = 0.8
exceptions = [

View File

@@ -132,6 +132,11 @@
"name": "cron.database",
"value": "postgres",
"vartype": "string"
},
{
"name": "session_preload_libraries",
"value": "anon",
"vartype": "string"
}
]
},

View File

@@ -35,11 +35,11 @@ for pg_version in ${TEST_VERSION_ONLY-14 15 16 17}; do
echo "clean up containers if exists"
cleanup
PG_TEST_VERSION=$((pg_version < 16 ? 16 : pg_version))
# The support of pg_anon not yet added to PG17, so we have to add the corresponding option for other PG versions
if [ "${pg_version}" -ne 17 ]; then
# The support of pg_anon not yet added to PG17, so we have to remove the corresponding option
if [ $pg_version -eq 17 ]; then
SPEC_PATH="compute_wrapper/var/db/postgres/specs"
mv $SPEC_PATH/spec.json $SPEC_PATH/spec.bak
jq '.cluster.settings += [{"name": "session_preload_libraries","value": "anon","vartype": "string"}]' "${SPEC_PATH}/spec.bak" > "${SPEC_PATH}/spec.json"
jq 'del(.cluster.settings[] | select (.name == "session_preload_libraries"))' $SPEC_PATH/spec.bak > $SPEC_PATH/spec.json
fi
PG_VERSION=$pg_version PG_TEST_VERSION=$PG_TEST_VERSION docker compose --profile test-extensions -f $COMPOSE_FILE up --build -d
@@ -106,8 +106,8 @@ for pg_version in ${TEST_VERSION_ONLY-14 15 16 17}; do
fi
fi
cleanup
# Restore the original spec.json
if [ "$pg_version" -ne 17 ]; then
mv "$SPEC_PATH/spec.bak" "$SPEC_PATH/spec.json"
# The support of pg_anon not yet added to PG17, so we have to remove the corresponding option
if [ $pg_version -eq 17 ]; then
mv $SPEC_PATH/spec.bak $SPEC_PATH/spec.json
fi
done

View File

@@ -1,5 +1,6 @@
//! Structs representing the JSON formats used in the compute_ctl's HTTP API.
use std::collections::HashSet;
use std::fmt::Display;
use chrono::{DateTime, Utc};
@@ -162,9 +163,8 @@ pub enum ControlPlaneComputeStatus {
#[derive(Clone, Debug, Default, Serialize)]
pub struct InstalledExtension {
pub extname: String,
pub version: String,
pub versions: HashSet<String>,
pub n_databases: u32, // Number of databases using this extension
pub owned_by_superuser: String,
}
#[derive(Clone, Debug, Default, Serialize)]

View File

@@ -19,10 +19,6 @@ pub type PgIdent = String;
/// String type alias representing Postgres extension version
pub type ExtVersion = String;
fn default_reconfigure_concurrency() -> usize {
1
}
/// Cluster spec or configuration represented as an optional number of
/// delta operations + final cluster state description.
#[derive(Clone, Debug, Default, Deserialize, Serialize)]
@@ -67,20 +63,11 @@ pub struct ComputeSpec {
#[serde(default)]
pub disk_quota_bytes: Option<u64>,
/// Disables the vm-monitor behavior that resizes LFC on upscale/downscale, instead relying on
/// the initial size of LFC.
///
/// This is intended for use when the LFC size is being overridden from the default but
/// autoscaling is still enabled, and we don't want the vm-monitor to interfere with the custom
/// LFC sizing.
#[serde(default)]
pub disable_lfc_resizing: Option<bool>,
/// Expected cluster state at the end of transition process.
pub cluster: Cluster,
pub delta_operations: Option<Vec<DeltaOp>>,
/// An optional hint that can be passed to speed up startup time if we know
/// An optinal hint that can be passed to speed up startup time if we know
/// that no pg catalog mutations (like role creation, database creation,
/// extension creation) need to be done on the actual database to start.
#[serde(default)] // Default false
@@ -99,7 +86,9 @@ pub struct ComputeSpec {
// etc. GUCs in cluster.settings. TODO: Once the control plane has been
// updated to fill these fields, we can make these non optional.
pub tenant_id: Option<TenantId>,
pub timeline_id: Option<TimelineId>,
pub pageserver_connstring: Option<String>,
#[serde(default)]
@@ -124,20 +113,6 @@ pub struct ComputeSpec {
/// Local Proxy configuration used for JWT authentication
#[serde(default)]
pub local_proxy_config: Option<LocalProxySpec>,
/// Number of concurrent connections during the parallel RunInEachDatabase
/// phase of the apply config process.
///
/// We need a higher concurrency during reconfiguration in case of many DBs,
/// but instance is already running and used by client. We can easily get out of
/// `max_connections` limit, and the current code won't handle that.
///
/// Default is 1, but also allow control plane to override this value for specific
/// projects. It's also recommended to bump `superuser_reserved_connections` +=
/// `reconfigure_concurrency` for such projects to ensure that we always have
/// enough spare connections for reconfiguration process to succeed.
#[serde(default = "default_reconfigure_concurrency")]
pub reconfigure_concurrency: usize,
}
/// Feature flag to signal `compute_ctl` to enable certain experimental functionality.
@@ -340,9 +315,6 @@ mod tests {
// Features list defaults to empty vector.
assert!(spec.features.is_empty());
// Reconfigure concurrency defaults to 1.
assert_eq!(spec.reconfigure_concurrency, 1);
}
#[test]

View File

@@ -91,7 +91,7 @@ impl Timing {
/// Return true if there is a ready event.
fn is_event_ready(&self, queue: &mut BinaryHeap<Pending>) -> bool {
queue.peek().is_some_and(|x| x.time <= self.now())
queue.peek().map_or(false, |x| x.time <= self.now())
}
/// Clear all pending events.

View File

@@ -75,7 +75,7 @@ pub struct TenantPolicyRequest {
pub scheduling: Option<ShardSchedulingPolicy>,
}
#[derive(Clone, Serialize, Deserialize, PartialEq, Eq, Hash, Debug, PartialOrd, Ord)]
#[derive(Clone, Serialize, Deserialize, PartialEq, Eq, Hash, Debug)]
pub struct AvailabilityZone(pub String);
impl Display for AvailabilityZone {
@@ -245,17 +245,6 @@ impl From<NodeAvailability> for NodeAvailabilityWrapper {
}
}
/// Scheduling policy enables us to selectively disable some automatic actions that the
/// controller performs on a tenant shard. This is only set to a non-default value by
/// human intervention, and it is reset to the default value (Active) when the tenant's
/// placement policy is modified away from Attached.
///
/// The typical use of a non-Active scheduling policy is one of:
/// - Pinnning a shard to a node (i.e. migrating it there & setting a non-Active scheduling policy)
/// - Working around a bug (e.g. if something is flapping and we need to stop it until the bug is fixed)
///
/// If you're not sure which policy to use to pin a shard to its current location, you probably
/// want Pause.
#[derive(Serialize, Deserialize, Clone, Copy, Eq, PartialEq, Debug)]
pub enum ShardSchedulingPolicy {
// Normal mode: the tenant's scheduled locations may be updated at will, including
@@ -372,23 +361,6 @@ pub struct MetadataHealthListOutdatedResponse {
pub health_records: Vec<MetadataHealthRecord>,
}
/// Publicly exposed safekeeper description
///
/// The `active` flag which we have in the DB is not included on purpose: it is deprecated.
#[derive(Serialize, Deserialize, Clone)]
pub struct SafekeeperDescribeResponse {
pub id: NodeId,
pub region_id: String,
/// 1 is special, it means just created (not currently posted to storcon).
/// Zero or negative is not really expected.
/// Otherwise the number from `release-$(number_of_commits_on_branch)` tag.
pub version: i64,
pub host: String,
pub port: i32,
pub http_port: i32,
pub availability_zone_id: String,
}
#[cfg(test)]
mod test {
use super::*;

View File

@@ -24,7 +24,7 @@ pub struct Key {
/// When working with large numbers of Keys in-memory, it is more efficient to handle them as i128 than as
/// a struct of fields.
#[derive(Clone, Copy, Hash, PartialEq, Eq, Ord, PartialOrd, Serialize, Deserialize, Debug)]
#[derive(Clone, Copy, Hash, PartialEq, Eq, Ord, PartialOrd, Serialize, Deserialize)]
pub struct CompactKey(i128);
/// The storage key size.
@@ -565,10 +565,6 @@ impl Key {
&& self.field5 == 0
&& self.field6 == u32::MAX
}
pub fn is_slru_dir_key(&self) -> bool {
slru_dir_kind(self).is_some()
}
}
#[inline(always)]

View File

@@ -6,7 +6,6 @@ pub mod utilization;
use camino::Utf8PathBuf;
pub use utilization::PageserverUtilization;
use core::ops::Range;
use std::{
collections::HashMap,
fmt::Display,
@@ -18,7 +17,7 @@ use std::{
use byteorder::{BigEndian, ReadBytesExt};
use postgres_ffi::BLCKSZ;
use serde::{Deserialize, Deserializer, Serialize, Serializer};
use serde::{Deserialize, Serialize};
use serde_with::serde_as;
use utils::{
completion,
@@ -29,7 +28,6 @@ use utils::{
};
use crate::{
key::Key,
reltag::RelTag,
shard::{ShardCount, ShardStripeSize, TenantShardId},
};
@@ -212,68 +210,6 @@ pub enum TimelineState {
Broken { reason: String, backtrace: String },
}
#[serde_with::serde_as]
#[derive(Debug, Clone, serde::Deserialize, serde::Serialize)]
pub struct CompactLsnRange {
pub start: Lsn,
pub end: Lsn,
}
#[serde_with::serde_as]
#[derive(Debug, Clone, serde::Deserialize, serde::Serialize)]
pub struct CompactKeyRange {
#[serde_as(as = "serde_with::DisplayFromStr")]
pub start: Key,
#[serde_as(as = "serde_with::DisplayFromStr")]
pub end: Key,
}
impl From<Range<Lsn>> for CompactLsnRange {
fn from(range: Range<Lsn>) -> Self {
Self {
start: range.start,
end: range.end,
}
}
}
impl From<Range<Key>> for CompactKeyRange {
fn from(range: Range<Key>) -> Self {
Self {
start: range.start,
end: range.end,
}
}
}
impl From<CompactLsnRange> for Range<Lsn> {
fn from(range: CompactLsnRange) -> Self {
range.start..range.end
}
}
impl From<CompactKeyRange> for Range<Key> {
fn from(range: CompactKeyRange) -> Self {
range.start..range.end
}
}
impl CompactLsnRange {
pub fn above(lsn: Lsn) -> Self {
Self {
start: lsn,
end: Lsn::MAX,
}
}
}
#[derive(Debug, Clone, Serialize)]
pub struct CompactInfoResponse {
pub compact_key_range: Option<CompactKeyRange>,
pub compact_lsn_range: Option<CompactLsnRange>,
pub sub_compaction: bool,
}
#[derive(Serialize, Deserialize, Clone)]
pub struct TimelineCreateRequest {
pub new_timeline_id: TimelineId,
@@ -389,115 +325,6 @@ impl Default for ShardParameters {
}
}
#[derive(Debug, Default, Clone, Eq, PartialEq)]
pub enum FieldPatch<T> {
Upsert(T),
Remove,
#[default]
Noop,
}
impl<T> FieldPatch<T> {
fn is_noop(&self) -> bool {
matches!(self, FieldPatch::Noop)
}
pub fn apply(self, target: &mut Option<T>) {
match self {
Self::Upsert(v) => *target = Some(v),
Self::Remove => *target = None,
Self::Noop => {}
}
}
pub fn map<U, E, F: FnOnce(T) -> Result<U, E>>(self, map: F) -> Result<FieldPatch<U>, E> {
match self {
Self::Upsert(v) => Ok(FieldPatch::<U>::Upsert(map(v)?)),
Self::Remove => Ok(FieldPatch::<U>::Remove),
Self::Noop => Ok(FieldPatch::<U>::Noop),
}
}
}
impl<'de, T: Deserialize<'de>> Deserialize<'de> for FieldPatch<T> {
fn deserialize<D>(deserializer: D) -> Result<Self, D::Error>
where
D: Deserializer<'de>,
{
Option::deserialize(deserializer).map(|opt| match opt {
None => FieldPatch::Remove,
Some(val) => FieldPatch::Upsert(val),
})
}
}
impl<T: Serialize> Serialize for FieldPatch<T> {
fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>
where
S: Serializer,
{
match self {
FieldPatch::Upsert(val) => serializer.serialize_some(val),
FieldPatch::Remove => serializer.serialize_none(),
FieldPatch::Noop => unreachable!(),
}
}
}
#[derive(Serialize, Deserialize, Debug, Default, Clone, Eq, PartialEq)]
#[serde(default)]
pub struct TenantConfigPatch {
#[serde(skip_serializing_if = "FieldPatch::is_noop")]
pub checkpoint_distance: FieldPatch<u64>,
#[serde(skip_serializing_if = "FieldPatch::is_noop")]
pub checkpoint_timeout: FieldPatch<String>,
#[serde(skip_serializing_if = "FieldPatch::is_noop")]
pub compaction_target_size: FieldPatch<u64>,
#[serde(skip_serializing_if = "FieldPatch::is_noop")]
pub compaction_period: FieldPatch<String>,
#[serde(skip_serializing_if = "FieldPatch::is_noop")]
pub compaction_threshold: FieldPatch<usize>,
// defer parsing compaction_algorithm, like eviction_policy
#[serde(skip_serializing_if = "FieldPatch::is_noop")]
pub compaction_algorithm: FieldPatch<CompactionAlgorithmSettings>,
#[serde(skip_serializing_if = "FieldPatch::is_noop")]
pub gc_horizon: FieldPatch<u64>,
#[serde(skip_serializing_if = "FieldPatch::is_noop")]
pub gc_period: FieldPatch<String>,
#[serde(skip_serializing_if = "FieldPatch::is_noop")]
pub image_creation_threshold: FieldPatch<usize>,
#[serde(skip_serializing_if = "FieldPatch::is_noop")]
pub pitr_interval: FieldPatch<String>,
#[serde(skip_serializing_if = "FieldPatch::is_noop")]
pub walreceiver_connect_timeout: FieldPatch<String>,
#[serde(skip_serializing_if = "FieldPatch::is_noop")]
pub lagging_wal_timeout: FieldPatch<String>,
#[serde(skip_serializing_if = "FieldPatch::is_noop")]
pub max_lsn_wal_lag: FieldPatch<NonZeroU64>,
#[serde(skip_serializing_if = "FieldPatch::is_noop")]
pub eviction_policy: FieldPatch<EvictionPolicy>,
#[serde(skip_serializing_if = "FieldPatch::is_noop")]
pub min_resident_size_override: FieldPatch<u64>,
#[serde(skip_serializing_if = "FieldPatch::is_noop")]
pub evictions_low_residence_duration_metric_threshold: FieldPatch<String>,
#[serde(skip_serializing_if = "FieldPatch::is_noop")]
pub heatmap_period: FieldPatch<String>,
#[serde(skip_serializing_if = "FieldPatch::is_noop")]
pub lazy_slru_download: FieldPatch<bool>,
#[serde(skip_serializing_if = "FieldPatch::is_noop")]
pub timeline_get_throttle: FieldPatch<ThrottleConfig>,
#[serde(skip_serializing_if = "FieldPatch::is_noop")]
pub image_layer_creation_check_threshold: FieldPatch<u8>,
#[serde(skip_serializing_if = "FieldPatch::is_noop")]
pub lsn_lease_length: FieldPatch<String>,
#[serde(skip_serializing_if = "FieldPatch::is_noop")]
pub lsn_lease_length_for_ts: FieldPatch<String>,
#[serde(skip_serializing_if = "FieldPatch::is_noop")]
pub timeline_offloading: FieldPatch<bool>,
#[serde(skip_serializing_if = "FieldPatch::is_noop")]
pub wal_receiver_protocol_override: FieldPatch<PostgresClientProtocol>,
}
/// An alternative representation of `pageserver::tenant::TenantConf` with
/// simpler types.
#[derive(Serialize, Deserialize, Debug, Default, Clone, Eq, PartialEq)]
@@ -529,107 +356,6 @@ pub struct TenantConfig {
pub wal_receiver_protocol_override: Option<PostgresClientProtocol>,
}
impl TenantConfig {
pub fn apply_patch(self, patch: TenantConfigPatch) -> TenantConfig {
let Self {
mut checkpoint_distance,
mut checkpoint_timeout,
mut compaction_target_size,
mut compaction_period,
mut compaction_threshold,
mut compaction_algorithm,
mut gc_horizon,
mut gc_period,
mut image_creation_threshold,
mut pitr_interval,
mut walreceiver_connect_timeout,
mut lagging_wal_timeout,
mut max_lsn_wal_lag,
mut eviction_policy,
mut min_resident_size_override,
mut evictions_low_residence_duration_metric_threshold,
mut heatmap_period,
mut lazy_slru_download,
mut timeline_get_throttle,
mut image_layer_creation_check_threshold,
mut lsn_lease_length,
mut lsn_lease_length_for_ts,
mut timeline_offloading,
mut wal_receiver_protocol_override,
} = self;
patch.checkpoint_distance.apply(&mut checkpoint_distance);
patch.checkpoint_timeout.apply(&mut checkpoint_timeout);
patch
.compaction_target_size
.apply(&mut compaction_target_size);
patch.compaction_period.apply(&mut compaction_period);
patch.compaction_threshold.apply(&mut compaction_threshold);
patch.compaction_algorithm.apply(&mut compaction_algorithm);
patch.gc_horizon.apply(&mut gc_horizon);
patch.gc_period.apply(&mut gc_period);
patch
.image_creation_threshold
.apply(&mut image_creation_threshold);
patch.pitr_interval.apply(&mut pitr_interval);
patch
.walreceiver_connect_timeout
.apply(&mut walreceiver_connect_timeout);
patch.lagging_wal_timeout.apply(&mut lagging_wal_timeout);
patch.max_lsn_wal_lag.apply(&mut max_lsn_wal_lag);
patch.eviction_policy.apply(&mut eviction_policy);
patch
.min_resident_size_override
.apply(&mut min_resident_size_override);
patch
.evictions_low_residence_duration_metric_threshold
.apply(&mut evictions_low_residence_duration_metric_threshold);
patch.heatmap_period.apply(&mut heatmap_period);
patch.lazy_slru_download.apply(&mut lazy_slru_download);
patch
.timeline_get_throttle
.apply(&mut timeline_get_throttle);
patch
.image_layer_creation_check_threshold
.apply(&mut image_layer_creation_check_threshold);
patch.lsn_lease_length.apply(&mut lsn_lease_length);
patch
.lsn_lease_length_for_ts
.apply(&mut lsn_lease_length_for_ts);
patch.timeline_offloading.apply(&mut timeline_offloading);
patch
.wal_receiver_protocol_override
.apply(&mut wal_receiver_protocol_override);
Self {
checkpoint_distance,
checkpoint_timeout,
compaction_target_size,
compaction_period,
compaction_threshold,
compaction_algorithm,
gc_horizon,
gc_period,
image_creation_threshold,
pitr_interval,
walreceiver_connect_timeout,
lagging_wal_timeout,
max_lsn_wal_lag,
eviction_policy,
min_resident_size_override,
evictions_low_residence_duration_metric_threshold,
heatmap_period,
lazy_slru_download,
timeline_get_throttle,
image_layer_creation_check_threshold,
lsn_lease_length,
lsn_lease_length_for_ts,
timeline_offloading,
wal_receiver_protocol_override,
}
}
}
/// The policy for the aux file storage.
///
/// It can be switched through `switch_aux_file_policy` tenant config.
@@ -960,14 +686,6 @@ impl TenantConfigRequest {
}
}
#[derive(Serialize, Deserialize, Debug)]
#[serde(deny_unknown_fields)]
pub struct TenantConfigPatchRequest {
pub tenant_id: TenantId,
#[serde(flatten)]
pub config: TenantConfigPatch, // as we have a flattened field, we should reject all unknown fields in it
}
/// See [`TenantState::attachment_status`] and the OpenAPI docs for context.
#[derive(Serialize, Deserialize, Clone)]
#[serde(tag = "slug", content = "data", rename_all = "snake_case")]
@@ -1460,91 +1178,75 @@ impl TryFrom<u8> for PagestreamBeMessageTag {
// interface allows sending both LSNs, and let the pageserver do the right thing. There was no
// difference in the responses between V1 and V2.
//
// V3 version of protocol adds request ID to all requests. This request ID is also included in response
// as well as other fields from requests, which allows to verify that we receive response for our request.
// We copy fields from request to response to make checking more reliable: request ID is formed from process ID
// and local counter, so in principle there can be duplicated requests IDs if process PID is reused.
//
#[derive(Debug, PartialEq, Eq, Clone, Copy)]
#[derive(Clone, Copy)]
pub enum PagestreamProtocolVersion {
V2,
V3,
}
pub type RequestId = u64;
#[derive(Debug, PartialEq, Eq, Clone, Copy)]
pub struct PagestreamRequest {
pub reqid: RequestId,
#[derive(Debug, PartialEq, Eq)]
pub struct PagestreamExistsRequest {
pub request_lsn: Lsn,
pub not_modified_since: Lsn,
}
#[derive(Debug, PartialEq, Eq, Clone, Copy)]
pub struct PagestreamExistsRequest {
pub hdr: PagestreamRequest,
pub rel: RelTag,
}
#[derive(Debug, PartialEq, Eq, Clone, Copy)]
#[derive(Debug, PartialEq, Eq)]
pub struct PagestreamNblocksRequest {
pub hdr: PagestreamRequest,
pub request_lsn: Lsn,
pub not_modified_since: Lsn,
pub rel: RelTag,
}
#[derive(Debug, PartialEq, Eq, Clone, Copy)]
#[derive(Debug, PartialEq, Eq)]
pub struct PagestreamGetPageRequest {
pub hdr: PagestreamRequest,
pub request_lsn: Lsn,
pub not_modified_since: Lsn,
pub rel: RelTag,
pub blkno: u32,
}
#[derive(Debug, PartialEq, Eq, Clone, Copy)]
#[derive(Debug, PartialEq, Eq)]
pub struct PagestreamDbSizeRequest {
pub hdr: PagestreamRequest,
pub request_lsn: Lsn,
pub not_modified_since: Lsn,
pub dbnode: u32,
}
#[derive(Debug, PartialEq, Eq, Clone, Copy)]
#[derive(Debug, PartialEq, Eq)]
pub struct PagestreamGetSlruSegmentRequest {
pub hdr: PagestreamRequest,
pub request_lsn: Lsn,
pub not_modified_since: Lsn,
pub kind: u8,
pub segno: u32,
}
#[derive(Debug)]
pub struct PagestreamExistsResponse {
pub req: PagestreamExistsRequest,
pub exists: bool,
}
#[derive(Debug)]
pub struct PagestreamNblocksResponse {
pub req: PagestreamNblocksRequest,
pub n_blocks: u32,
}
#[derive(Debug)]
pub struct PagestreamGetPageResponse {
pub req: PagestreamGetPageRequest,
pub page: Bytes,
}
#[derive(Debug)]
pub struct PagestreamGetSlruSegmentResponse {
pub req: PagestreamGetSlruSegmentRequest,
pub segment: Bytes,
}
#[derive(Debug)]
pub struct PagestreamErrorResponse {
pub req: PagestreamRequest,
pub message: String,
}
#[derive(Debug)]
pub struct PagestreamDbSizeResponse {
pub req: PagestreamDbSizeRequest,
pub db_size: i64,
}
@@ -1561,16 +1263,15 @@ pub struct TenantHistorySize {
impl PagestreamFeMessage {
/// Serialize a compute -> pageserver message. This is currently only used in testing
/// tools. Always uses protocol version 3.
/// tools. Always uses protocol version 2.
pub fn serialize(&self) -> Bytes {
let mut bytes = BytesMut::new();
match self {
Self::Exists(req) => {
bytes.put_u8(0);
bytes.put_u64(req.hdr.reqid);
bytes.put_u64(req.hdr.request_lsn.0);
bytes.put_u64(req.hdr.not_modified_since.0);
bytes.put_u64(req.request_lsn.0);
bytes.put_u64(req.not_modified_since.0);
bytes.put_u32(req.rel.spcnode);
bytes.put_u32(req.rel.dbnode);
bytes.put_u32(req.rel.relnode);
@@ -1579,9 +1280,8 @@ impl PagestreamFeMessage {
Self::Nblocks(req) => {
bytes.put_u8(1);
bytes.put_u64(req.hdr.reqid);
bytes.put_u64(req.hdr.request_lsn.0);
bytes.put_u64(req.hdr.not_modified_since.0);
bytes.put_u64(req.request_lsn.0);
bytes.put_u64(req.not_modified_since.0);
bytes.put_u32(req.rel.spcnode);
bytes.put_u32(req.rel.dbnode);
bytes.put_u32(req.rel.relnode);
@@ -1590,9 +1290,8 @@ impl PagestreamFeMessage {
Self::GetPage(req) => {
bytes.put_u8(2);
bytes.put_u64(req.hdr.reqid);
bytes.put_u64(req.hdr.request_lsn.0);
bytes.put_u64(req.hdr.not_modified_since.0);
bytes.put_u64(req.request_lsn.0);
bytes.put_u64(req.not_modified_since.0);
bytes.put_u32(req.rel.spcnode);
bytes.put_u32(req.rel.dbnode);
bytes.put_u32(req.rel.relnode);
@@ -1602,17 +1301,15 @@ impl PagestreamFeMessage {
Self::DbSize(req) => {
bytes.put_u8(3);
bytes.put_u64(req.hdr.reqid);
bytes.put_u64(req.hdr.request_lsn.0);
bytes.put_u64(req.hdr.not_modified_since.0);
bytes.put_u64(req.request_lsn.0);
bytes.put_u64(req.not_modified_since.0);
bytes.put_u32(req.dbnode);
}
Self::GetSlruSegment(req) => {
bytes.put_u8(4);
bytes.put_u64(req.hdr.reqid);
bytes.put_u64(req.hdr.request_lsn.0);
bytes.put_u64(req.hdr.not_modified_since.0);
bytes.put_u64(req.request_lsn.0);
bytes.put_u64(req.not_modified_since.0);
bytes.put_u8(req.kind);
bytes.put_u32(req.segno);
}
@@ -1621,35 +1318,21 @@ impl PagestreamFeMessage {
bytes.into()
}
pub fn parse<R: std::io::Read>(
body: &mut R,
protocol_version: PagestreamProtocolVersion,
) -> anyhow::Result<PagestreamFeMessage> {
pub fn parse<R: std::io::Read>(body: &mut R) -> anyhow::Result<PagestreamFeMessage> {
// these correspond to the NeonMessageTag enum in pagestore_client.h
//
// TODO: consider using protobuf or serde bincode for less error prone
// serialization.
let msg_tag = body.read_u8()?;
let (reqid, request_lsn, not_modified_since) = match protocol_version {
PagestreamProtocolVersion::V2 => (
0,
Lsn::from(body.read_u64::<BigEndian>()?),
Lsn::from(body.read_u64::<BigEndian>()?),
),
PagestreamProtocolVersion::V3 => (
body.read_u64::<BigEndian>()?,
Lsn::from(body.read_u64::<BigEndian>()?),
Lsn::from(body.read_u64::<BigEndian>()?),
),
};
// these two fields are the same for every request type
let request_lsn = Lsn::from(body.read_u64::<BigEndian>()?);
let not_modified_since = Lsn::from(body.read_u64::<BigEndian>()?);
match msg_tag {
0 => Ok(PagestreamFeMessage::Exists(PagestreamExistsRequest {
hdr: PagestreamRequest {
reqid,
request_lsn,
not_modified_since,
},
request_lsn,
not_modified_since,
rel: RelTag {
spcnode: body.read_u32::<BigEndian>()?,
dbnode: body.read_u32::<BigEndian>()?,
@@ -1658,11 +1341,8 @@ impl PagestreamFeMessage {
},
})),
1 => Ok(PagestreamFeMessage::Nblocks(PagestreamNblocksRequest {
hdr: PagestreamRequest {
reqid,
request_lsn,
not_modified_since,
},
request_lsn,
not_modified_since,
rel: RelTag {
spcnode: body.read_u32::<BigEndian>()?,
dbnode: body.read_u32::<BigEndian>()?,
@@ -1671,11 +1351,8 @@ impl PagestreamFeMessage {
},
})),
2 => Ok(PagestreamFeMessage::GetPage(PagestreamGetPageRequest {
hdr: PagestreamRequest {
reqid,
request_lsn,
not_modified_since,
},
request_lsn,
not_modified_since,
rel: RelTag {
spcnode: body.read_u32::<BigEndian>()?,
dbnode: body.read_u32::<BigEndian>()?,
@@ -1685,20 +1362,14 @@ impl PagestreamFeMessage {
blkno: body.read_u32::<BigEndian>()?,
})),
3 => Ok(PagestreamFeMessage::DbSize(PagestreamDbSizeRequest {
hdr: PagestreamRequest {
reqid,
request_lsn,
not_modified_since,
},
request_lsn,
not_modified_since,
dbnode: body.read_u32::<BigEndian>()?,
})),
4 => Ok(PagestreamFeMessage::GetSlruSegment(
PagestreamGetSlruSegmentRequest {
hdr: PagestreamRequest {
reqid,
request_lsn,
not_modified_since,
},
request_lsn,
not_modified_since,
kind: body.read_u8()?,
segno: body.read_u32::<BigEndian>()?,
},
@@ -1709,114 +1380,43 @@ impl PagestreamFeMessage {
}
impl PagestreamBeMessage {
pub fn serialize(&self, protocol_version: PagestreamProtocolVersion) -> Bytes {
pub fn serialize(&self) -> Bytes {
let mut bytes = BytesMut::new();
use PagestreamBeMessageTag as Tag;
match protocol_version {
PagestreamProtocolVersion::V2 => {
match self {
Self::Exists(resp) => {
bytes.put_u8(Tag::Exists as u8);
bytes.put_u8(resp.exists as u8);
}
Self::Nblocks(resp) => {
bytes.put_u8(Tag::Nblocks as u8);
bytes.put_u32(resp.n_blocks);
}
Self::GetPage(resp) => {
bytes.put_u8(Tag::GetPage as u8);
bytes.put(&resp.page[..])
}
Self::Error(resp) => {
bytes.put_u8(Tag::Error as u8);
bytes.put(resp.message.as_bytes());
bytes.put_u8(0); // null terminator
}
Self::DbSize(resp) => {
bytes.put_u8(Tag::DbSize as u8);
bytes.put_i64(resp.db_size);
}
Self::GetSlruSegment(resp) => {
bytes.put_u8(Tag::GetSlruSegment as u8);
bytes.put_u32((resp.segment.len() / BLCKSZ as usize) as u32);
bytes.put(&resp.segment[..]);
}
}
match self {
Self::Exists(resp) => {
bytes.put_u8(Tag::Exists as u8);
bytes.put_u8(resp.exists as u8);
}
PagestreamProtocolVersion::V3 => {
match self {
Self::Exists(resp) => {
bytes.put_u8(Tag::Exists as u8);
bytes.put_u64(resp.req.hdr.reqid);
bytes.put_u64(resp.req.hdr.request_lsn.0);
bytes.put_u64(resp.req.hdr.not_modified_since.0);
bytes.put_u32(resp.req.rel.spcnode);
bytes.put_u32(resp.req.rel.dbnode);
bytes.put_u32(resp.req.rel.relnode);
bytes.put_u8(resp.req.rel.forknum);
bytes.put_u8(resp.exists as u8);
}
Self::Nblocks(resp) => {
bytes.put_u8(Tag::Nblocks as u8);
bytes.put_u64(resp.req.hdr.reqid);
bytes.put_u64(resp.req.hdr.request_lsn.0);
bytes.put_u64(resp.req.hdr.not_modified_since.0);
bytes.put_u32(resp.req.rel.spcnode);
bytes.put_u32(resp.req.rel.dbnode);
bytes.put_u32(resp.req.rel.relnode);
bytes.put_u8(resp.req.rel.forknum);
bytes.put_u32(resp.n_blocks);
}
Self::Nblocks(resp) => {
bytes.put_u8(Tag::Nblocks as u8);
bytes.put_u32(resp.n_blocks);
}
Self::GetPage(resp) => {
bytes.put_u8(Tag::GetPage as u8);
bytes.put_u64(resp.req.hdr.reqid);
bytes.put_u64(resp.req.hdr.request_lsn.0);
bytes.put_u64(resp.req.hdr.not_modified_since.0);
bytes.put_u32(resp.req.rel.spcnode);
bytes.put_u32(resp.req.rel.dbnode);
bytes.put_u32(resp.req.rel.relnode);
bytes.put_u8(resp.req.rel.forknum);
bytes.put_u32(resp.req.blkno);
bytes.put(&resp.page[..])
}
Self::GetPage(resp) => {
bytes.put_u8(Tag::GetPage as u8);
bytes.put(&resp.page[..]);
}
Self::Error(resp) => {
bytes.put_u8(Tag::Error as u8);
bytes.put_u64(resp.req.reqid);
bytes.put_u64(resp.req.request_lsn.0);
bytes.put_u64(resp.req.not_modified_since.0);
bytes.put(resp.message.as_bytes());
bytes.put_u8(0); // null terminator
}
Self::DbSize(resp) => {
bytes.put_u8(Tag::DbSize as u8);
bytes.put_u64(resp.req.hdr.reqid);
bytes.put_u64(resp.req.hdr.request_lsn.0);
bytes.put_u64(resp.req.hdr.not_modified_since.0);
bytes.put_u32(resp.req.dbnode);
bytes.put_i64(resp.db_size);
}
Self::Error(resp) => {
bytes.put_u8(Tag::Error as u8);
bytes.put(resp.message.as_bytes());
bytes.put_u8(0); // null terminator
}
Self::DbSize(resp) => {
bytes.put_u8(Tag::DbSize as u8);
bytes.put_i64(resp.db_size);
}
Self::GetSlruSegment(resp) => {
bytes.put_u8(Tag::GetSlruSegment as u8);
bytes.put_u64(resp.req.hdr.reqid);
bytes.put_u64(resp.req.hdr.request_lsn.0);
bytes.put_u64(resp.req.hdr.not_modified_since.0);
bytes.put_u8(resp.req.kind);
bytes.put_u32(resp.req.segno);
bytes.put_u32((resp.segment.len() / BLCKSZ as usize) as u32);
bytes.put(&resp.segment[..]);
}
}
Self::GetSlruSegment(resp) => {
bytes.put_u8(Tag::GetSlruSegment as u8);
bytes.put_u32((resp.segment.len() / BLCKSZ as usize) as u32);
bytes.put(&resp.segment[..]);
}
}
bytes.into()
}
@@ -1828,131 +1428,38 @@ impl PagestreamBeMessage {
let ok =
match Tag::try_from(msg_tag).map_err(|tag: u8| anyhow::anyhow!("invalid tag {tag}"))? {
Tag::Exists => {
let reqid = buf.read_u64::<BigEndian>()?;
let request_lsn = Lsn(buf.read_u64::<BigEndian>()?);
let not_modified_since = Lsn(buf.read_u64::<BigEndian>()?);
let rel = RelTag {
spcnode: buf.read_u32::<BigEndian>()?,
dbnode: buf.read_u32::<BigEndian>()?,
relnode: buf.read_u32::<BigEndian>()?,
forknum: buf.read_u8()?,
};
let exists = buf.read_u8()? != 0;
let exists = buf.read_u8()?;
Self::Exists(PagestreamExistsResponse {
req: PagestreamExistsRequest {
hdr: PagestreamRequest {
reqid,
request_lsn,
not_modified_since,
},
rel,
},
exists,
exists: exists != 0,
})
}
Tag::Nblocks => {
let reqid = buf.read_u64::<BigEndian>()?;
let request_lsn = Lsn(buf.read_u64::<BigEndian>()?);
let not_modified_since = Lsn(buf.read_u64::<BigEndian>()?);
let rel = RelTag {
spcnode: buf.read_u32::<BigEndian>()?,
dbnode: buf.read_u32::<BigEndian>()?,
relnode: buf.read_u32::<BigEndian>()?,
forknum: buf.read_u8()?,
};
let n_blocks = buf.read_u32::<BigEndian>()?;
Self::Nblocks(PagestreamNblocksResponse {
req: PagestreamNblocksRequest {
hdr: PagestreamRequest {
reqid,
request_lsn,
not_modified_since,
},
rel,
},
n_blocks,
})
Self::Nblocks(PagestreamNblocksResponse { n_blocks })
}
Tag::GetPage => {
let reqid = buf.read_u64::<BigEndian>()?;
let request_lsn = Lsn(buf.read_u64::<BigEndian>()?);
let not_modified_since = Lsn(buf.read_u64::<BigEndian>()?);
let rel = RelTag {
spcnode: buf.read_u32::<BigEndian>()?,
dbnode: buf.read_u32::<BigEndian>()?,
relnode: buf.read_u32::<BigEndian>()?,
forknum: buf.read_u8()?,
};
let blkno = buf.read_u32::<BigEndian>()?;
let mut page = vec![0; 8192]; // TODO: use MaybeUninit
buf.read_exact(&mut page)?;
Self::GetPage(PagestreamGetPageResponse {
req: PagestreamGetPageRequest {
hdr: PagestreamRequest {
reqid,
request_lsn,
not_modified_since,
},
rel,
blkno,
},
page: page.into(),
})
PagestreamBeMessage::GetPage(PagestreamGetPageResponse { page: page.into() })
}
Tag::Error => {
let reqid = buf.read_u64::<BigEndian>()?;
let request_lsn = Lsn(buf.read_u64::<BigEndian>()?);
let not_modified_since = Lsn(buf.read_u64::<BigEndian>()?);
let mut msg = Vec::new();
buf.read_until(0, &mut msg)?;
let cstring = std::ffi::CString::from_vec_with_nul(msg)?;
let rust_str = cstring.to_str()?;
Self::Error(PagestreamErrorResponse {
req: PagestreamRequest {
reqid,
request_lsn,
not_modified_since,
},
PagestreamBeMessage::Error(PagestreamErrorResponse {
message: rust_str.to_owned(),
})
}
Tag::DbSize => {
let reqid = buf.read_u64::<BigEndian>()?;
let request_lsn = Lsn(buf.read_u64::<BigEndian>()?);
let not_modified_since = Lsn(buf.read_u64::<BigEndian>()?);
let dbnode = buf.read_u32::<BigEndian>()?;
let db_size = buf.read_i64::<BigEndian>()?;
Self::DbSize(PagestreamDbSizeResponse {
req: PagestreamDbSizeRequest {
hdr: PagestreamRequest {
reqid,
request_lsn,
not_modified_since,
},
dbnode,
},
db_size,
})
Self::DbSize(PagestreamDbSizeResponse { db_size })
}
Tag::GetSlruSegment => {
let reqid = buf.read_u64::<BigEndian>()?;
let request_lsn = Lsn(buf.read_u64::<BigEndian>()?);
let not_modified_since = Lsn(buf.read_u64::<BigEndian>()?);
let kind = buf.read_u8()?;
let segno = buf.read_u32::<BigEndian>()?;
let n_blocks = buf.read_u32::<BigEndian>()?;
let mut segment = vec![0; n_blocks as usize * BLCKSZ as usize];
buf.read_exact(&mut segment)?;
Self::GetSlruSegment(PagestreamGetSlruSegmentResponse {
req: PagestreamGetSlruSegmentRequest {
hdr: PagestreamRequest {
reqid,
request_lsn,
not_modified_since,
},
kind,
segno,
},
segment: segment.into(),
})
}
@@ -1991,11 +1498,8 @@ mod tests {
// Test serialization/deserialization of PagestreamFeMessage
let messages = vec![
PagestreamFeMessage::Exists(PagestreamExistsRequest {
hdr: PagestreamRequest {
reqid: 0,
request_lsn: Lsn(4),
not_modified_since: Lsn(3),
},
request_lsn: Lsn(4),
not_modified_since: Lsn(3),
rel: RelTag {
forknum: 1,
spcnode: 2,
@@ -2004,11 +1508,8 @@ mod tests {
},
}),
PagestreamFeMessage::Nblocks(PagestreamNblocksRequest {
hdr: PagestreamRequest {
reqid: 0,
request_lsn: Lsn(4),
not_modified_since: Lsn(4),
},
request_lsn: Lsn(4),
not_modified_since: Lsn(4),
rel: RelTag {
forknum: 1,
spcnode: 2,
@@ -2017,11 +1518,8 @@ mod tests {
},
}),
PagestreamFeMessage::GetPage(PagestreamGetPageRequest {
hdr: PagestreamRequest {
reqid: 0,
request_lsn: Lsn(4),
not_modified_since: Lsn(3),
},
request_lsn: Lsn(4),
not_modified_since: Lsn(3),
rel: RelTag {
forknum: 1,
spcnode: 2,
@@ -2031,19 +1529,14 @@ mod tests {
blkno: 7,
}),
PagestreamFeMessage::DbSize(PagestreamDbSizeRequest {
hdr: PagestreamRequest {
reqid: 0,
request_lsn: Lsn(4),
not_modified_since: Lsn(3),
},
request_lsn: Lsn(4),
not_modified_since: Lsn(3),
dbnode: 7,
}),
];
for msg in messages {
let bytes = msg.serialize();
let reconstructed =
PagestreamFeMessage::parse(&mut bytes.reader(), PagestreamProtocolVersion::V3)
.unwrap();
let reconstructed = PagestreamFeMessage::parse(&mut bytes.reader()).unwrap();
assert!(msg == reconstructed);
}
}
@@ -2206,45 +1699,4 @@ mod tests {
);
}
}
#[test]
fn test_tenant_config_patch_request_serde() {
let patch_request = TenantConfigPatchRequest {
tenant_id: TenantId::from_str("17c6d121946a61e5ab0fe5a2fd4d8215").unwrap(),
config: TenantConfigPatch {
checkpoint_distance: FieldPatch::Upsert(42),
gc_horizon: FieldPatch::Remove,
compaction_threshold: FieldPatch::Noop,
..TenantConfigPatch::default()
},
};
let json = serde_json::to_string(&patch_request).unwrap();
let expected = r#"{"tenant_id":"17c6d121946a61e5ab0fe5a2fd4d8215","checkpoint_distance":42,"gc_horizon":null}"#;
assert_eq!(json, expected);
let decoded: TenantConfigPatchRequest = serde_json::from_str(&json).unwrap();
assert_eq!(decoded.tenant_id, patch_request.tenant_id);
assert_eq!(decoded.config, patch_request.config);
// Now apply the patch to a config to demonstrate semantics
let base = TenantConfig {
checkpoint_distance: Some(28),
gc_horizon: Some(100),
compaction_target_size: Some(1024),
..Default::default()
};
let expected = TenantConfig {
checkpoint_distance: Some(42),
gc_horizon: None,
..base.clone()
};
let patched = base.apply_patch(decoded.config);
assert_eq!(patched, expected);
}
}

View File

@@ -158,8 +158,7 @@ impl ShardIdentity {
key_to_shard_number(self.count, self.stripe_size, key)
}
/// Return true if the key is stored only on this shard. This does not include
/// global keys, see is_key_global().
/// Return true if the key should be ingested by this shard
///
/// Shards must ingest _at least_ keys which return true from this check.
pub fn is_key_local(&self, key: &Key) -> bool {
@@ -172,12 +171,8 @@ impl ShardIdentity {
}
/// Return true if the key should be stored on all shards, not just one.
pub fn is_key_global(&self, key: &Key) -> bool {
if key.is_slru_block_key()
|| key.is_slru_segment_size_key()
|| key.is_aux_file_key()
|| key.is_slru_dir_key()
{
fn is_key_global(&self, key: &Key) -> bool {
if key.is_slru_block_key() || key.is_slru_segment_size_key() || key.is_aux_file_key() {
// Special keys that are only stored on shard 0
false
} else if key.is_rel_block_key() {

View File

@@ -9,11 +9,9 @@ regex.workspace = true
bytes.workspace = true
anyhow.workspace = true
crc32c.workspace = true
criterion.workspace = true
once_cell.workspace = true
log.workspace = true
memoffset.workspace = true
pprof.workspace = true
thiserror.workspace = true
serde.workspace = true
utils.workspace = true
@@ -26,7 +24,3 @@ postgres.workspace = true
[build-dependencies]
anyhow.workspace = true
bindgen.workspace = true
[[bench]]
name = "waldecoder"
harness = false

View File

@@ -1,26 +0,0 @@
## Benchmarks
To run benchmarks:
```sh
# All benchmarks.
cargo bench --package postgres_ffi
# Specific file.
cargo bench --package postgres_ffi --bench waldecoder
# Specific benchmark.
cargo bench --package postgres_ffi --bench waldecoder complete_record/size=1024
# List available benchmarks.
cargo bench --package postgres_ffi --benches -- --list
# Generate flamegraph profiles using pprof-rs, profiling for 10 seconds.
# Output in target/criterion/*/profile/flamegraph.svg.
cargo bench --package postgres_ffi --bench waldecoder complete_record/size=1024 -- --profile-time 10
```
Additional charts and statistics are available in `target/criterion/report/index.html`.
Benchmarks are automatically compared against the previous run. To compare against other runs, see
`--baseline` and `--save-baseline`.

View File

@@ -1,49 +0,0 @@
use std::ffi::CStr;
use criterion::{criterion_group, criterion_main, Bencher, Criterion};
use postgres_ffi::v17::wal_generator::LogicalMessageGenerator;
use postgres_ffi::v17::waldecoder_handler::WalStreamDecoderHandler;
use postgres_ffi::waldecoder::WalStreamDecoder;
use pprof::criterion::{Output, PProfProfiler};
use utils::lsn::Lsn;
const KB: usize = 1024;
// Register benchmarks with Criterion.
criterion_group!(
name = benches;
config = Criterion::default().with_profiler(PProfProfiler::new(100, Output::Flamegraph(None)));
targets = bench_complete_record,
);
criterion_main!(benches);
/// Benchmarks WalStreamDecoder::complete_record() for a logical message of varying size.
fn bench_complete_record(c: &mut Criterion) {
let mut g = c.benchmark_group("complete_record");
for size in [64, KB, 8 * KB, 128 * KB] {
// Kind of weird to change the group throughput per benchmark, but it's the only way
// to vary it per benchmark. It works.
g.throughput(criterion::Throughput::Bytes(size as u64));
g.bench_function(format!("size={size}"), |b| run_bench(b, size).unwrap());
}
fn run_bench(b: &mut Bencher, size: usize) -> anyhow::Result<()> {
const PREFIX: &CStr = c"";
let value_size = LogicalMessageGenerator::make_value_size(size, PREFIX);
let value = vec![1; value_size];
let mut decoder = WalStreamDecoder::new(Lsn(0), 170000);
let msg = LogicalMessageGenerator::new(PREFIX, &value)
.next()
.unwrap()
.encode(Lsn(0));
assert_eq!(msg.len(), size);
b.iter(|| {
let msg = msg.clone(); // Bytes::clone() is cheap
decoder.complete_record(msg).unwrap();
});
Ok(())
}
}

View File

@@ -106,11 +106,11 @@ impl<R: RecordGenerator> WalGenerator<R> {
const TIMELINE_ID: u32 = 1;
/// Creates a new WAL generator with the given record generator.
pub fn new(record_generator: R, start_lsn: Lsn) -> WalGenerator<R> {
pub fn new(record_generator: R) -> WalGenerator<R> {
Self {
record_generator,
lsn: start_lsn,
prev_lsn: start_lsn,
lsn: Lsn(0),
prev_lsn: Lsn(0),
}
}
@@ -231,22 +231,6 @@ impl LogicalMessageGenerator {
};
[&header.encode(), prefix, message].concat().into()
}
/// Computes how large a value must be to get a record of the given size. Convenience method to
/// construct records of pre-determined size. Panics if the record size is too small.
pub fn make_value_size(record_size: usize, prefix: &CStr) -> usize {
let xlog_header_size = XLOG_SIZE_OF_XLOG_RECORD;
let lm_header_size = size_of::<XlLogicalMessage>();
let prefix_size = prefix.to_bytes_with_nul().len();
let data_header_size = match record_size - xlog_header_size - 2 {
0..=255 => 2,
256..=258 => panic!("impossible record_size {record_size}"),
259.. => 5,
};
record_size
.checked_sub(xlog_header_size + lm_header_size + prefix_size + data_header_size)
.expect("record_size too small")
}
}
impl Iterator for LogicalMessageGenerator {

View File

@@ -81,7 +81,7 @@ fn test_end_of_wal<C: crate::Crafter>(test_name: &str) {
continue;
}
let mut f = File::options().write(true).open(file.path()).unwrap();
static ZEROS: [u8; WAL_SEGMENT_SIZE] = [0u8; WAL_SEGMENT_SIZE];
const ZEROS: [u8; WAL_SEGMENT_SIZE] = [0u8; WAL_SEGMENT_SIZE];
f.write_all(
&ZEROS[0..min(
WAL_SEGMENT_SIZE,

View File

@@ -1,7 +1,7 @@
[package]
name = "postgres-protocol2"
version = "0.1.0"
edition = "2021"
edition = "2018"
license = "MIT/Apache-2.0"
[dependencies]

View File

@@ -9,7 +9,8 @@
//!
//! This library assumes that the `client_encoding` backend parameter has been
//! set to `UTF8`. It will most likely not behave properly if that is not the case.
#![warn(missing_docs, clippy::all)]
#![doc(html_root_url = "https://docs.rs/postgres-protocol/0.6")]
#![warn(missing_docs, rust_2018_idioms, clippy::all)]
use byteorder::{BigEndian, ByteOrder};
use bytes::{BufMut, BytesMut};

View File

@@ -3,6 +3,7 @@
use byteorder::{BigEndian, ByteOrder};
use bytes::{Buf, BufMut, BytesMut};
use std::convert::TryFrom;
use std::error::Error;
use std::io;
use std::marker;

View File

@@ -1,7 +1,7 @@
[package]
name = "postgres-types2"
version = "0.1.0"
edition = "2021"
edition = "2018"
license = "MIT/Apache-2.0"
[dependencies]

View File

@@ -2,7 +2,8 @@
//!
//! This crate is used by the `tokio-postgres` and `postgres` crates. You normally don't need to depend directly on it
//! unless you want to define your own `ToSql` or `FromSql` definitions.
#![warn(clippy::all, missing_docs)]
#![doc(html_root_url = "https://docs.rs/postgres-types/0.2")]
#![warn(clippy::all, rust_2018_idioms, missing_docs)]
use fallible_iterator::FallibleIterator;
use postgres_protocol2::types;

View File

@@ -1,7 +1,7 @@
[package]
name = "tokio-postgres2"
version = "0.1.0"
edition = "2021"
edition = "2018"
license = "MIT/Apache-2.0"
[dependencies]

View File

@@ -33,12 +33,8 @@ pub struct Response {
#[derive(PartialEq, Debug)]
enum State {
Active,
Closing,
}
enum WriteReady {
Terminating,
WaitingOnRead,
Closing,
}
/// A connection to a PostgreSQL database.
@@ -55,6 +51,7 @@ pub struct Connection<S, T> {
/// HACK: we need this in the Neon Proxy to forward params.
pub parameters: HashMap<String, String>,
receiver: mpsc::UnboundedReceiver<Request>,
pending_request: Option<RequestMessages>,
pending_responses: VecDeque<BackendMessage>,
responses: VecDeque<Response>,
state: State,
@@ -75,6 +72,7 @@ where
stream,
parameters,
receiver,
pending_request: None,
pending_responses,
responses: VecDeque::new(),
state: State::Active,
@@ -95,23 +93,26 @@ where
.map(|o| o.map(|r| r.map_err(Error::io)))
}
/// Read and process messages from the connection to postgres.
/// client <- postgres
fn poll_read(&mut self, cx: &mut Context<'_>) -> Poll<Result<AsyncMessage, Error>> {
fn poll_read(&mut self, cx: &mut Context<'_>) -> Result<Option<AsyncMessage>, Error> {
if self.state != State::Active {
trace!("poll_read: done");
return Ok(None);
}
loop {
let message = match self.poll_response(cx)? {
Poll::Ready(Some(message)) => message,
Poll::Ready(None) => return Poll::Ready(Err(Error::closed())),
Poll::Ready(None) => return Err(Error::closed()),
Poll::Pending => {
trace!("poll_read: waiting on response");
return Poll::Pending;
return Ok(None);
}
};
let (mut messages, request_complete) = match message {
BackendMessage::Async(Message::NoticeResponse(body)) => {
let error = DbError::parse(&mut body.fields()).map_err(Error::parse)?;
return Poll::Ready(Ok(AsyncMessage::Notice(error)));
return Ok(Some(AsyncMessage::Notice(error)));
}
BackendMessage::Async(Message::NotificationResponse(body)) => {
let notification = Notification {
@@ -119,7 +120,7 @@ where
channel: body.channel().map_err(Error::parse)?.to_string(),
payload: body.message().map_err(Error::parse)?.to_string(),
};
return Poll::Ready(Ok(AsyncMessage::Notification(notification)));
return Ok(Some(AsyncMessage::Notification(notification)));
}
BackendMessage::Async(Message::ParameterStatus(body)) => {
self.parameters.insert(
@@ -138,10 +139,8 @@ where
let mut response = match self.responses.pop_front() {
Some(response) => response,
None => match messages.next().map_err(Error::parse)? {
Some(Message::ErrorResponse(error)) => {
return Poll::Ready(Err(Error::db(error)))
}
_ => return Poll::Ready(Err(Error::unexpected_message())),
Some(Message::ErrorResponse(error)) => return Err(Error::db(error)),
_ => return Err(Error::unexpected_message()),
},
};
@@ -165,14 +164,18 @@ where
request_complete,
});
trace!("poll_read: waiting on sender");
return Poll::Pending;
return Ok(None);
}
}
}
}
/// Fetch the next client request and enqueue the response sender.
fn poll_request(&mut self, cx: &mut Context<'_>) -> Poll<Option<RequestMessages>> {
if let Some(messages) = self.pending_request.take() {
trace!("retrying pending request");
return Poll::Ready(Some(messages));
}
if self.receiver.is_closed() {
return Poll::Ready(None);
}
@@ -190,80 +193,74 @@ where
}
}
/// Process client requests and write them to the postgres connection, flushing if necessary.
/// client -> postgres
fn poll_write(&mut self, cx: &mut Context<'_>) -> Poll<Result<WriteReady, Error>> {
fn poll_write(&mut self, cx: &mut Context<'_>) -> Result<bool, Error> {
loop {
if self.state == State::Closing {
trace!("poll_write: done");
return Ok(false);
}
if Pin::new(&mut self.stream)
.poll_ready(cx)
.map_err(Error::io)?
.is_pending()
{
trace!("poll_write: waiting on socket");
// poll_ready is self-flushing.
return Poll::Pending;
return Ok(false);
}
match self.poll_request(cx) {
// send the message to postgres
Poll::Ready(Some(RequestMessages::Single(request))) => {
Pin::new(&mut self.stream)
.start_send(request)
.map_err(Error::io)?;
}
// No more messages from the client, and no more responses to wait for.
// Send a terminate message to postgres
Poll::Ready(None) if self.responses.is_empty() => {
let request = match self.poll_request(cx) {
Poll::Ready(Some(request)) => request,
Poll::Ready(None) if self.responses.is_empty() && self.state == State::Active => {
trace!("poll_write: at eof, terminating");
self.state = State::Terminating;
let mut request = BytesMut::new();
frontend::terminate(&mut request);
let request = FrontendMessage::Raw(request.freeze());
Pin::new(&mut self.stream)
.start_send(request)
.map_err(Error::io)?;
trace!("poll_write: sent eof, closing");
trace!("poll_write: done");
return Poll::Ready(Ok(WriteReady::Terminating));
RequestMessages::Single(FrontendMessage::Raw(request.freeze()))
}
// No more messages from the client, but there are still some responses to wait for.
Poll::Ready(None) => {
trace!(
"poll_write: at eof, pending responses {}",
self.responses.len()
);
ready!(self.poll_flush(cx))?;
return Poll::Ready(Ok(WriteReady::WaitingOnRead));
return Ok(true);
}
// Still waiting for a message from the client.
Poll::Pending => {
trace!("poll_write: waiting on request");
ready!(self.poll_flush(cx))?;
return Poll::Pending;
return Ok(true);
}
};
match request {
RequestMessages::Single(request) => {
Pin::new(&mut self.stream)
.start_send(request)
.map_err(Error::io)?;
if self.state == State::Terminating {
trace!("poll_write: sent eof, closing");
self.state = State::Closing;
}
}
}
}
}
fn poll_flush(&mut self, cx: &mut Context<'_>) -> Poll<Result<(), Error>> {
fn poll_flush(&mut self, cx: &mut Context<'_>) -> Result<(), Error> {
match Pin::new(&mut self.stream)
.poll_flush(cx)
.map_err(Error::io)?
{
Poll::Ready(()) => {
trace!("poll_flush: flushed");
Poll::Ready(Ok(()))
}
Poll::Pending => {
trace!("poll_flush: waiting on socket");
Poll::Pending
}
Poll::Ready(()) => trace!("poll_flush: flushed"),
Poll::Pending => trace!("poll_flush: waiting on socket"),
}
Ok(())
}
fn poll_shutdown(&mut self, cx: &mut Context<'_>) -> Poll<Result<(), Error>> {
if self.state != State::Closing {
return Poll::Pending;
}
match Pin::new(&mut self.stream)
.poll_close(cx)
.map_err(Error::io)?
@@ -292,30 +289,18 @@ where
&mut self,
cx: &mut Context<'_>,
) -> Poll<Option<Result<AsyncMessage, Error>>> {
if self.state != State::Closing {
// if the state is still active, try read from and write to postgres.
let message = self.poll_read(cx)?;
let closing = self.poll_write(cx)?;
if let Poll::Ready(WriteReady::Terminating) = closing {
self.state = State::Closing;
}
if let Poll::Ready(message) = message {
return Poll::Ready(Some(Ok(message)));
}
// poll_read returned Pending.
// poll_write returned Pending or Ready(WriteReady::WaitingOnRead).
// if poll_write returned Ready(WriteReady::WaitingOnRead), then we are waiting to read more data from postgres.
if self.state != State::Closing {
return Poll::Pending;
}
let message = self.poll_read(cx)?;
let want_flush = self.poll_write(cx)?;
if want_flush {
self.poll_flush(cx)?;
}
match self.poll_shutdown(cx) {
Poll::Ready(Ok(())) => Poll::Ready(None),
Poll::Ready(Err(e)) => Poll::Ready(Some(Err(e))),
Poll::Pending => Poll::Pending,
match message {
Some(message) => Poll::Ready(Some(Ok(message))),
None => match self.poll_shutdown(cx) {
Poll::Ready(Ok(())) => Poll::Ready(None),
Poll::Ready(Err(e)) => Poll::Ready(Some(Err(e))),
Poll::Pending => Poll::Pending,
},
}
}
}

View File

@@ -1,5 +1,5 @@
//! An asynchronous, pipelined, PostgreSQL client.
#![warn(clippy::all)]
#![warn(rust_2018_idioms, clippy::all)]
pub use crate::cancel_token::CancelToken;
pub use crate::client::{Client, SocketConfig};

View File

@@ -11,7 +11,7 @@ mod private {
Query(&'a str),
}
impl ToStatementType<'_> {
impl<'a> ToStatementType<'a> {
pub async fn into_statement(self, client: &Client) -> Result<Statement, Error> {
match self {
ToStatementType::Statement(s) => Ok(s.clone()),

View File

@@ -18,7 +18,6 @@ camino = { workspace = true, features = ["serde1"] }
humantime-serde.workspace = true
hyper = { workspace = true, features = ["client"] }
futures.workspace = true
reqwest.workspace = true
serde.workspace = true
serde_json.workspace = true
tokio = { workspace = true, features = ["sync", "fs", "io-util"] }

View File

@@ -13,12 +13,10 @@ use std::time::Duration;
use std::time::SystemTime;
use super::REMOTE_STORAGE_PREFIX_SEPARATOR;
use anyhow::Context;
use anyhow::Result;
use azure_core::request_options::{IfMatchCondition, MaxResults, Metadata, Range};
use azure_core::HttpClient;
use azure_core::TransportOptions;
use azure_core::{Continuable, RetryOptions};
use azure_identity::DefaultAzureCredential;
use azure_storage::StorageCredentials;
use azure_storage_blobs::blob::CopyStatus;
use azure_storage_blobs::prelude::ClientBuilder;
@@ -78,18 +76,12 @@ impl AzureBlobStorage {
let credentials = if let Ok(access_key) = env::var("AZURE_STORAGE_ACCESS_KEY") {
StorageCredentials::access_key(account.clone(), access_key)
} else {
let token_credential = azure_identity::create_default_credential()
.context("trying to obtain Azure default credentials")?;
StorageCredentials::token_credential(token_credential)
let token_credential = DefaultAzureCredential::default();
StorageCredentials::token_credential(Arc::new(token_credential))
};
let builder = ClientBuilder::new(account, credentials)
// we have an outer retry
.retry(RetryOptions::none())
// Customize transport to configure conneciton pooling
.transport(TransportOptions::new(Self::reqwest_client(
azure_config.conn_pool_size,
)));
// we have an outer retry
let builder = ClientBuilder::new(account, credentials).retry(RetryOptions::none());
let client = builder.container_client(azure_config.container_name.to_owned());
@@ -114,14 +106,6 @@ impl AzureBlobStorage {
})
}
fn reqwest_client(conn_pool_size: usize) -> Arc<dyn HttpClient> {
let client = reqwest::ClientBuilder::new()
.pool_max_idle_per_host(conn_pool_size)
.build()
.expect("failed to build `reqwest` client");
Arc::new(client)
}
pub fn relative_path_to_name(&self, path: &RemotePath) -> String {
assert_eq!(std::path::MAIN_SEPARATOR, REMOTE_STORAGE_PREFIX_SEPARATOR);
let path_string = path.get_path().as_str();
@@ -560,9 +544,9 @@ impl RemoteStorage for AzureBlobStorage {
.await
}
async fn delete_objects(
async fn delete_objects<'a>(
&self,
paths: &[RemotePath],
paths: &'a [RemotePath],
cancel: &CancellationToken,
) -> anyhow::Result<()> {
let kind = RequestKind::Delete;
@@ -640,10 +624,6 @@ impl RemoteStorage for AzureBlobStorage {
res
}
fn max_keys_per_delete(&self) -> usize {
super::MAX_KEYS_PER_DELETE_AZURE
}
async fn copy(
&self,
from: &RemotePath,

View File

@@ -114,16 +114,6 @@ fn default_max_keys_per_list_response() -> Option<i32> {
DEFAULT_MAX_KEYS_PER_LIST_RESPONSE
}
fn default_azure_conn_pool_size() -> usize {
// Conservative default: no connection pooling. At time of writing this is the Azure
// SDK's default as well, due to historic reports of hard-to-reproduce issues
// (https://github.com/hyperium/hyper/issues/2312)
//
// However, using connection pooling is important to avoid exhausting client ports when
// doing huge numbers of requests (https://github.com/neondatabase/cloud/issues/20971)
0
}
impl Debug for S3Config {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
f.debug_struct("S3Config")
@@ -156,8 +146,6 @@ pub struct AzureConfig {
pub concurrency_limit: NonZeroUsize,
#[serde(default = "default_max_keys_per_list_response")]
pub max_keys_per_list_response: Option<i32>,
#[serde(default = "default_azure_conn_pool_size")]
pub conn_pool_size: usize,
}
fn default_remote_storage_azure_concurrency_limit() -> NonZeroUsize {
@@ -314,7 +302,6 @@ timeout = '5s'";
container_region = 'westeurope'
upload_storage_class = 'INTELLIGENT_TIERING'
timeout = '7s'
conn_pool_size = 8
";
let config = parse(toml).unwrap();
@@ -329,7 +316,6 @@ timeout = '5s'";
prefix_in_container: None,
concurrency_limit: default_remote_storage_azure_concurrency_limit(),
max_keys_per_list_response: DEFAULT_MAX_KEYS_PER_LIST_RESPONSE,
conn_pool_size: 8,
}),
timeout: Duration::from_secs(7),
small_timeout: RemoteStorageConfig::DEFAULT_SMALL_TIMEOUT

View File

@@ -70,14 +70,7 @@ pub const DEFAULT_REMOTE_STORAGE_AZURE_CONCURRENCY_LIMIT: usize = 100;
pub const DEFAULT_MAX_KEYS_PER_LIST_RESPONSE: Option<i32> = None;
/// As defined in S3 docs
///
/// <https://docs.aws.amazon.com/AmazonS3/latest/API/API_DeleteObjects.html>
pub const MAX_KEYS_PER_DELETE_S3: usize = 1000;
/// As defined in Azure docs
///
/// <https://learn.microsoft.com/en-us/rest/api/storageservices/blob-batch>
pub const MAX_KEYS_PER_DELETE_AZURE: usize = 256;
pub const MAX_KEYS_PER_DELETE: usize = 1000;
const REMOTE_STORAGE_PREFIX_SEPARATOR: char = '/';
@@ -341,20 +334,12 @@ pub trait RemoteStorage: Send + Sync + 'static {
/// If the operation fails because of timeout or cancellation, the root cause of the error will be
/// set to `TimeoutOrCancel`. In such situation it is unknown which deletions, if any, went
/// through.
async fn delete_objects(
async fn delete_objects<'a>(
&self,
paths: &[RemotePath],
paths: &'a [RemotePath],
cancel: &CancellationToken,
) -> anyhow::Result<()>;
/// Returns the maximum number of keys that a call to [`Self::delete_objects`] can delete without chunking
///
/// The value returned is only an optimization hint, One can pass larger number of objects to
/// `delete_objects` as well.
///
/// The value is guaranteed to be >= 1.
fn max_keys_per_delete(&self) -> usize;
/// Deletes all objects matching the given prefix.
///
/// NB: this uses NoDelimiter and will match partial prefixes. For example, the prefix /a/b will
@@ -548,16 +533,6 @@ impl<Other: RemoteStorage> GenericRemoteStorage<Arc<Other>> {
}
}
/// [`RemoteStorage::max_keys_per_delete`]
pub fn max_keys_per_delete(&self) -> usize {
match self {
Self::LocalFs(s) => s.max_keys_per_delete(),
Self::AwsS3(s) => s.max_keys_per_delete(),
Self::AzureBlob(s) => s.max_keys_per_delete(),
Self::Unreliable(s) => s.max_keys_per_delete(),
}
}
/// See [`RemoteStorage::delete_prefix`]
pub async fn delete_prefix(
&self,

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