Compare commits

..

1 Commits

Author SHA1 Message Date
Owen Brady
c93ac95d25 pageserver_api: implement keyspace range iterator (#6435) 2025-02-12 20:07:39 +00:00
493 changed files with 7710 additions and 14674 deletions

View File

@@ -14,7 +14,6 @@
!compute/
!compute_tools/
!control_plane/
!docker-compose/ext-src
!libs/
!pageserver/
!pgxn/

View File

@@ -28,7 +28,3 @@ config-variables:
- DEV_AWS_OIDC_ROLE_MANAGE_BENCHMARK_EC2_VMS_ARN
- SLACK_ON_CALL_STORAGE_STAGING_STREAM
- SLACK_CICD_CHANNEL_ID
- SLACK_STORAGE_CHANNEL_ID
- NEON_DEV_AWS_ACCOUNT_ID
- NEON_PROD_AWS_ACCOUNT_ID
- AWS_ECR_REGION

View File

@@ -38,11 +38,9 @@ runs:
#
- name: Set variables
shell: bash -euxo pipefail {0}
env:
PR_NUMBER: ${{ github.event.pull_request.number }}
BUCKET: neon-github-public-dev
run: |
if [ -n "${PR_NUMBER}" ]; then
PR_NUMBER=$(jq --raw-output .pull_request.number "$GITHUB_EVENT_PATH" || true)
if [ "${PR_NUMBER}" != "null" ]; then
BRANCH_OR_PR=pr-${PR_NUMBER}
elif [ "${GITHUB_REF_NAME}" = "main" ] || [ "${GITHUB_REF_NAME}" = "release" ] || \
[ "${GITHUB_REF_NAME}" = "release-proxy" ] || [ "${GITHUB_REF_NAME}" = "release-compute" ]; then
@@ -61,6 +59,8 @@ runs:
echo "LOCK_FILE=${LOCK_FILE}" >> $GITHUB_ENV
echo "WORKDIR=${WORKDIR}" >> $GITHUB_ENV
echo "BUCKET=${BUCKET}" >> $GITHUB_ENV
env:
BUCKET: neon-github-public-dev
# TODO: We can replace with a special docker image with Java and Allure pre-installed
- uses: actions/setup-java@v4
@@ -80,8 +80,8 @@ runs:
rm -f ${ALLURE_ZIP}
fi
env:
ALLURE_VERSION: 2.32.2
ALLURE_ZIP_SHA256: 3f28885e2118f6317c92f667eaddcc6491400af1fb9773c1f3797a5fa5174953
ALLURE_VERSION: 2.27.0
ALLURE_ZIP_SHA256: b071858fb2fa542c65d8f152c5c40d26267b2dfb74df1f1608a589ecca38e777
- uses: aws-actions/configure-aws-credentials@v4
if: ${{ !cancelled() }}

View File

@@ -18,11 +18,9 @@ runs:
steps:
- name: Set variables
shell: bash -euxo pipefail {0}
env:
PR_NUMBER: ${{ github.event.pull_request.number }}
REPORT_DIR: ${{ inputs.report-dir }}
run: |
if [ -n "${PR_NUMBER}" ]; then
PR_NUMBER=$(jq --raw-output .pull_request.number "$GITHUB_EVENT_PATH" || true)
if [ "${PR_NUMBER}" != "null" ]; then
BRANCH_OR_PR=pr-${PR_NUMBER}
elif [ "${GITHUB_REF_NAME}" = "main" ] || [ "${GITHUB_REF_NAME}" = "release" ] || \
[ "${GITHUB_REF_NAME}" = "release-proxy" ] || [ "${GITHUB_REF_NAME}" = "release-compute" ]; then
@@ -34,6 +32,8 @@ runs:
echo "BRANCH_OR_PR=${BRANCH_OR_PR}" >> $GITHUB_ENV
echo "REPORT_DIR=${REPORT_DIR}" >> $GITHUB_ENV
env:
REPORT_DIR: ${{ inputs.report-dir }}
- uses: aws-actions/configure-aws-credentials@v4
if: ${{ !cancelled() }}

View File

@@ -19,11 +19,7 @@ inputs:
default: '[1, 1]'
# settings below only needed if you want the project to be sharded from the beginning
shard_split_project:
description: 'by default new projects are not shard-split initiailly, but only when shard-split threshold is reached, specify true to explicitly shard-split initially'
required: false
default: 'false'
disable_sharding:
description: 'by default new projects use storage controller default policy to shard-split when shard-split threshold is reached, specify true to explicitly disable sharding'
description: 'by default new projects are not shard-split, specify true to shard-split'
required: false
default: 'false'
admin_api_key:
@@ -111,21 +107,6 @@ runs:
-H "Accept: application/json" -H "Content-Type: application/json" -H "Authorization: Bearer ${ADMIN_API_KEY}" \
-d "{\"new_shard_count\": $SHARD_COUNT, \"new_stripe_size\": $STRIPE_SIZE}"
fi
if [ "${DISABLE_SHARDING}" = "true" ]; then
# determine tenant ID
TENANT_ID=`${PSQL} ${dsn} -t -A -c "SHOW neon.tenant_id"`
echo "Explicitly disabling shard-splitting for project ${project_id} with tenant_id ${TENANT_ID}"
echo "Sending PUT request to https://${API_HOST}/regions/${REGION_ID}/api/v1/admin/storage/proxy/control/v1/tenant/${TENANT_ID}/policy"
echo "with body {\"scheduling\": \"Essential\"}"
# we need an ADMIN API KEY to invoke storage controller API for shard splitting (bash -u above checks that the variable is set)
curl -X PUT \
"https://${API_HOST}/regions/${REGION_ID}/api/v1/admin/storage/proxy/control/v1/tenant/${TENANT_ID}/policy" \
-H "Accept: application/json" -H "Content-Type: application/json" -H "Authorization: Bearer ${ADMIN_API_KEY}" \
-d "{\"scheduling\": \"Essential\"}"
fi
env:
API_HOST: ${{ inputs.api_host }}
@@ -135,7 +116,6 @@ runs:
MIN_CU: ${{ fromJSON(inputs.compute_units)[0] }}
MAX_CU: ${{ fromJSON(inputs.compute_units)[1] }}
SHARD_SPLIT_PROJECT: ${{ inputs.shard_split_project }}
DISABLE_SHARDING: ${{ inputs.disable_sharding }}
ADMIN_API_KEY: ${{ inputs.admin_api_key }}
SHARD_COUNT: ${{ inputs.shard_count }}
STRIPE_SIZE: ${{ inputs.stripe_size }}

View File

@@ -236,5 +236,5 @@ runs:
uses: ./.github/actions/allure-report-store
with:
report-dir: /tmp/test_output/allure/results
unique-key: ${{ inputs.build_type }}-${{ inputs.pg_version }}-${{ runner.arch }}
unique-key: ${{ inputs.build_type }}-${{ inputs.pg_version }}
aws-oicd-role-arn: ${{ inputs.aws-oicd-role-arn }}

View File

@@ -337,7 +337,7 @@ jobs:
- name: Pytest regression tests
continue-on-error: ${{ matrix.lfc_state == 'with-lfc' && inputs.build-type == 'debug' }}
uses: ./.github/actions/run-python-test-set
timeout-minutes: ${{ inputs.sanitizers != 'enabled' && 75 || 180 }}
timeout-minutes: ${{ inputs.sanitizers != 'enabled' && 60 || 180 }}
with:
build_type: ${{ inputs.build-type }}
test_selection: regress
@@ -348,10 +348,6 @@ jobs:
rerun_failed: true
pg_version: ${{ matrix.pg_version }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
# `--session-timeout` is equal to (timeout-minutes - 10 minutes) * 60 seconds.
# Attempt to stop tests gracefully to generate test reports
# until they are forcibly stopped by the stricter `timeout-minutes` limit.
extra_params: --session-timeout=${{ inputs.sanitizers != 'enabled' && 3000 || 10200 }}
env:
TEST_RESULT_CONNSTR: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
CHECK_ONDISK_DATA_COMPATIBILITY: nonempty

View File

@@ -2,7 +2,7 @@ name: Push images to Container Registry
on:
workflow_call:
inputs:
# Example: {"docker.io/neondatabase/neon:13196061314":["${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}.dkr.ecr.${{ vars.AWS_ECR_REGION }}.amazonaws.com/neon:13196061314","neoneastus2.azurecr.io/neondatabase/neon:13196061314"]}
# Example: {"docker.io/neondatabase/neon:13196061314":["369495373322.dkr.ecr.eu-central-1.amazonaws.com/neon:13196061314","neoneastus2.azurecr.io/neondatabase/neon:13196061314"]}
image-map:
description: JSON map of images, mapping from a source image to an array of target images that should be pushed.
required: true
@@ -11,12 +11,8 @@ on:
description: AWS region to log in to. Required when pushing to ECR.
required: false
type: string
aws-account-id:
description: AWS account ID to log in to for pushing to ECR. Required when pushing to ECR.
required: false
type: string
aws-role-to-assume:
description: AWS role to assume to for pushing to ECR. Required when pushing to ECR.
aws-account-ids:
description: Comma separated AWS account IDs to log in to for pushing to ECR. Required when pushing to ECR.
required: false
type: string
azure-client-id:
@@ -35,6 +31,16 @@ on:
description: ACR registry name. Required when pushing to ACR.
required: false
type: string
secrets:
docker-hub-username:
description: Docker Hub username. Required when pushing to Docker Hub.
required: false
docker-hub-password:
description: Docker Hub password. Required when pushing to Docker Hub.
required: false
aws-role-to-assume:
description: AWS role to assume. Required when pushing to ECR.
required: false
permissions: {}
@@ -47,7 +53,6 @@ jobs:
runs-on: ubuntu-22.04
permissions:
id-token: write # Required for aws/azure login
packages: write # required for pushing to GHCR
steps:
- uses: actions/checkout@v4
with:
@@ -62,14 +67,14 @@ jobs:
uses: aws-actions/configure-aws-credentials@v4
with:
aws-region: "${{ inputs.aws-region }}"
role-to-assume: "arn:aws:iam::${{ inputs.aws-account-id }}:role/${{ inputs.aws-role-to-assume }}"
role-to-assume: "${{ secrets.aws-role-to-assume }}"
role-duration-seconds: 3600
- name: Login to ECR
if: contains(inputs.image-map, 'amazonaws.com/')
uses: aws-actions/amazon-ecr-login@v2
with:
registries: "${{ inputs.aws-account-id }}"
registries: "${{ inputs.aws-account-ids }}"
- name: Configure Azure credentials
if: contains(inputs.image-map, 'azurecr.io/')
@@ -84,19 +89,11 @@ jobs:
run: |
az acr login --name=${{ inputs.acr-registry-name }}
- name: Login to GHCR
if: contains(inputs.image-map, 'ghcr.io/')
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.repository_owner }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Log in to Docker Hub
uses: docker/login-action@v3
with:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
username: ${{ secrets.docker-hub-username }}
password: ${{ secrets.docker-hub-password }}
- name: Copy docker images to target registries
run: python scripts/push_with_image_map.py

View File

@@ -398,9 +398,6 @@ jobs:
runs-on: ${{ matrix.runner }}
container:
image: ${{ matrix.image }}
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
options: --init
# Increase timeout to 8h, default timeout is 6h

View File

@@ -68,7 +68,7 @@ jobs:
tag:
needs: [ check-permissions ]
runs-on: [ self-hosted, small ]
container: ${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}.dkr.ecr.${{ vars.AWS_ECR_REGION }}.amazonaws.com/base:pinned
container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/base:pinned
outputs:
build-tag: ${{steps.build-tag.outputs.tag}}
@@ -263,9 +263,8 @@ jobs:
echo "json=$(jq --compact-output '.' /tmp/benchmark_durations.json)" >> $GITHUB_OUTPUT
benchmarks:
# `!failure() && !cancelled()` is required because the workflow depends on the job that can be skipped: `deploy` in PRs
if: github.ref_name == 'main' || (contains(github.event.pull_request.labels.*.name, 'run-benchmarks') && !failure() && !cancelled())
needs: [ check-permissions, build-build-tools-image, get-benchmarks-durations, deploy ]
if: github.ref_name == 'main' || contains(github.event.pull_request.labels.*.name, 'run-benchmarks')
needs: [ check-permissions, build-and-test-locally, build-build-tools-image, get-benchmarks-durations ]
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
@@ -722,14 +721,14 @@ jobs:
- pg: v17
debian: bookworm
env:
VM_BUILDER_VERSION: v0.42.2
VM_BUILDER_VERSION: v0.37.1
steps:
- uses: actions/checkout@v4
- name: Downloading vm-builder
run: |
curl -fL https://github.com/neondatabase/autoscaling/releases/download/$VM_BUILDER_VERSION/vm-builder-amd64 -o vm-builder
curl -fL https://github.com/neondatabase/autoscaling/releases/download/$VM_BUILDER_VERSION/vm-builder -o vm-builder
chmod +x vm-builder
- uses: neondatabase/dev-actions/set-docker-config-dir@6094485bf440001c94a94a3f9e221e81ff6b6193
@@ -750,8 +749,7 @@ jobs:
-size=2G \
-spec=compute/vm-image-spec-${{ matrix.version.debian }}.yaml \
-src=neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }} \
-dst=neondatabase/vm-compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }} \
-target-arch=linux/amd64
-dst=neondatabase/vm-compute-node-${{ matrix.version.pg }}:${{ needs.tag.outputs.build-tag }}
- name: Pushing vm-compute-node image
run: |
@@ -860,79 +858,72 @@ jobs:
BRANCH: "${{ github.ref_name }}"
DEV_ACR: "${{ vars.AZURE_DEV_REGISTRY_NAME }}"
PROD_ACR: "${{ vars.AZURE_PROD_REGISTRY_NAME }}"
DEV_AWS: "${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}"
PROD_AWS: "${{ vars.NEON_PROD_AWS_ACCOUNT_ID }}"
AWS_REGION: "${{ vars.AWS_ECR_REGION }}"
push-neon-image-dev:
needs: [ generate-image-maps, neon-image ]
uses: ./.github/workflows/_push-to-container-registry.yml
permissions:
id-token: write # Required for aws/azure login
packages: write # required for pushing to GHCR
with:
image-map: '${{ needs.generate-image-maps.outputs.neon-dev }}'
aws-region: ${{ vars.AWS_ECR_REGION }}
aws-account-id: "${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}"
aws-role-to-assume: "gha-oidc-neon-admin"
aws-region: eu-central-1
aws-account-ids: "369495373322"
azure-client-id: ${{ vars.AZURE_DEV_CLIENT_ID }}
azure-subscription-id: ${{ vars.AZURE_DEV_SUBSCRIPTION_ID }}
azure-tenant-id: ${{ vars.AZURE_TENANT_ID }}
acr-registry-name: ${{ vars.AZURE_DEV_REGISTRY_NAME }}
secrets: inherit
secrets:
aws-role-to-assume: "${{ vars.DEV_AWS_OIDC_ROLE_ARN }}"
docker-hub-username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
docker-hub-password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
push-compute-image-dev:
needs: [ generate-image-maps, vm-compute-node-image ]
uses: ./.github/workflows/_push-to-container-registry.yml
permissions:
id-token: write # Required for aws/azure login
packages: write # required for pushing to GHCR
with:
image-map: '${{ needs.generate-image-maps.outputs.compute-dev }}'
aws-region: ${{ vars.AWS_ECR_REGION }}
aws-account-id: "${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}"
aws-role-to-assume: "gha-oidc-neon-admin"
aws-region: eu-central-1
aws-account-ids: "369495373322"
azure-client-id: ${{ vars.AZURE_DEV_CLIENT_ID }}
azure-subscription-id: ${{ vars.AZURE_DEV_SUBSCRIPTION_ID }}
azure-tenant-id: ${{ vars.AZURE_TENANT_ID }}
acr-registry-name: ${{ vars.AZURE_DEV_REGISTRY_NAME }}
secrets: inherit
secrets:
aws-role-to-assume: "${{ vars.DEV_AWS_OIDC_ROLE_ARN }}"
docker-hub-username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
docker-hub-password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
push-neon-image-prod:
if: github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
if: github.ref_name == 'main' || github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
needs: [ generate-image-maps, neon-image, test-images ]
uses: ./.github/workflows/_push-to-container-registry.yml
permissions:
id-token: write # Required for aws/azure login
packages: write # required for pushing to GHCR
with:
image-map: '${{ needs.generate-image-maps.outputs.neon-prod }}'
aws-region: ${{ vars.AWS_ECR_REGION }}
aws-account-id: "${{ vars.NEON_PROD_AWS_ACCOUNT_ID }}"
aws-role-to-assume: "gha-oidc-neon-admin"
aws-region: eu-central-1
aws-account-ids: "093970136003"
azure-client-id: ${{ vars.AZURE_PROD_CLIENT_ID }}
azure-subscription-id: ${{ vars.AZURE_PROD_SUBSCRIPTION_ID }}
azure-tenant-id: ${{ vars.AZURE_TENANT_ID }}
acr-registry-name: ${{ vars.AZURE_PROD_REGISTRY_NAME }}
secrets: inherit
secrets:
aws-role-to-assume: "${{ secrets.PROD_GHA_OIDC_ROLE }}"
docker-hub-username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
docker-hub-password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
push-compute-image-prod:
if: github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
if: github.ref_name == 'main' || github.ref_name == 'release' || github.ref_name == 'release-proxy' || github.ref_name == 'release-compute'
needs: [ generate-image-maps, vm-compute-node-image, test-images ]
uses: ./.github/workflows/_push-to-container-registry.yml
permissions:
id-token: write # Required for aws/azure login
packages: write # required for pushing to GHCR
with:
image-map: '${{ needs.generate-image-maps.outputs.compute-prod }}'
aws-region: ${{ vars.AWS_ECR_REGION }}
aws-account-id: "${{ vars.NEON_PROD_AWS_ACCOUNT_ID }}"
aws-role-to-assume: "gha-oidc-neon-admin"
aws-region: eu-central-1
aws-account-ids: "093970136003"
azure-client-id: ${{ vars.AZURE_PROD_CLIENT_ID }}
azure-subscription-id: ${{ vars.AZURE_PROD_SUBSCRIPTION_ID }}
azure-tenant-id: ${{ vars.AZURE_TENANT_ID }}
acr-registry-name: ${{ vars.AZURE_PROD_REGISTRY_NAME }}
secrets: inherit
secrets:
aws-role-to-assume: "${{ secrets.PROD_GHA_OIDC_ROLE }}"
docker-hub-username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
docker-hub-password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
# This is a bit of a special case so we're not using a generated image map.
add-latest-tag-to-neon-extensions-test-image:
@@ -945,7 +936,9 @@ jobs:
"docker.io/neondatabase/neon-test-extensions-v16:${{ needs.tag.outputs.build-tag }}": ["docker.io/neondatabase/neon-test-extensions-v16:latest"],
"docker.io/neondatabase/neon-test-extensions-v17:${{ needs.tag.outputs.build-tag }}": ["docker.io/neondatabase/neon-test-extensions-v17:latest"]
}
secrets: inherit
secrets:
docker-hub-username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
docker-hub-password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
trigger-custom-extensions-build-and-wait:
needs: [ check-permissions, tag ]
@@ -1035,7 +1028,7 @@ jobs:
statuses: write
contents: write
runs-on: [ self-hosted, small ]
container: ${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}.dkr.ecr.${{ vars.AWS_ECR_REGION }}.amazonaws.com/ansible:latest
container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/ansible:latest
steps:
- uses: actions/checkout@v4
@@ -1184,22 +1177,6 @@ jobs:
exit 1
fi
notify-storage-release-deploy-failure:
needs: [ deploy ]
# We want this to run even if (transitive) dependencies are skipped, because deploy should really be successful on release branch workflow runs.
if: github.ref_name == 'release' && needs.deploy.result != 'success' && always()
runs-on: ubuntu-22.04
steps:
- name: Post release-deploy failure to team-storage slack channel
uses: slackapi/slack-github-action@v2
with:
method: chat.postMessage
token: ${{ secrets.SLACK_BOT_TOKEN }}
payload: |
channel: ${{ vars.SLACK_STORAGE_CHANNEL_ID }}
text: |
🔴 @oncall-storage: deploy job on release branch had unexpected status "${{ needs.deploy.result }}" <${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}|GitHub Run>.
# The job runs on `release` branch and copies compatibility data and Neon artifact from the last *release PR* to the latest directory
promote-compatibility-data:
needs: [ deploy ]
@@ -1296,7 +1273,7 @@ jobs:
done
pin-build-tools-image:
needs: [ build-build-tools-image, test-images, build-and-test-locally ]
needs: [ build-build-tools-image, push-compute-image-prod, push-neon-image-prod, build-and-test-locally ]
if: github.ref_name == 'main'
uses: ./.github/workflows/pin-build-tools-image.yml
with:

View File

@@ -27,7 +27,7 @@ env:
jobs:
tag:
runs-on: [ self-hosted, small ]
container: ${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}.dkr.ecr.${{ vars.AWS_ECR_REGION }}.amazonaws.com/base:pinned
container: 369495373322.dkr.ecr.eu-central-1.amazonaws.com/base:pinned
outputs:
build-tag: ${{steps.build-tag.outputs.tag}}

View File

@@ -38,9 +38,6 @@ jobs:
runs-on: us-east-2
container:
image: neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
options: --init
steps:

View File

@@ -1,76 +0,0 @@
name: Force Test Upgrading of Extension
on:
schedule:
# * is a special character in YAML so you have to quote this string
# ┌───────────── minute (0 - 59)
# │ ┌───────────── hour (0 - 23)
# │ │ ┌───────────── day of the month (1 - 31)
# │ │ │ ┌───────────── month (1 - 12 or JAN-DEC)
# │ │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
- cron: '45 2 * * *' # run once a day, timezone is utc
workflow_dispatch: # adds ability to run this manually
defaults:
run:
shell: bash -euxo pipefail {0}
concurrency:
# Allow only one workflow
group: ${{ github.workflow }}
cancel-in-progress: true
permissions:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: read
jobs:
regress:
strategy:
fail-fast: false
matrix:
pg-version: [16, 17]
runs-on: small
steps:
- uses: actions/checkout@v4
with:
submodules: false
- name: Get the last compute release tag
id: get-last-compute-release-tag
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
tag=$(gh api -q '[.[].tag_name | select(startswith("release-compute"))][0]'\
-H "Accept: application/vnd.github+json" \
-H "X-GitHub-Api-Version: 2022-11-28" \
"/repos/${GITHUB_REPOSITORY}/releases")
echo tag=${tag} >> ${GITHUB_OUTPUT}
- name: Test extension upgrade
timeout-minutes: 20
env:
NEWTAG: latest
OLDTAG: ${{ steps.get-last-compute-release-tag.outputs.tag }}
PG_VERSION: ${{ matrix.pg-version }}
FORCE_ALL_UPGRADE_TESTS: true
run: ./docker-compose/test_extensions_upgrade.sh
- name: Print logs and clean up
if: always()
run: |
docker compose --profile test-extensions -f ./docker-compose/docker-compose.yml logs || true
docker compose --profile test-extensions -f ./docker-compose/docker-compose.yml down
- name: Post to the Slack channel
if: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@v1
with:
channel-id: ${{ vars.SLACK_ON_CALL_QA_STAGING_STREAM }}
slack-message: |
Test upgrading of extensions: ${{ job.status }}
<${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}|GitHub Run>
env:
SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}

View File

@@ -32,27 +32,18 @@ jobs:
- target_project: new_empty_project_stripe_size_2048
stripe_size: 2048 # 16 MiB
postgres_version: 16
disable_sharding: false
- target_project: new_empty_project_stripe_size_32768
stripe_size: 32768 # 256 MiB # note that this is different from null because using null will shard_split the project only if it reaches the threshold
# while here it is sharded from the beginning with a shard size of 256 MiB
disable_sharding: false
postgres_version: 16
- target_project: new_empty_project
stripe_size: null # run with neon defaults which will shard split only when reaching the threshold
disable_sharding: false
postgres_version: 16
- target_project: new_empty_project
stripe_size: null # run with neon defaults which will shard split only when reaching the threshold
disable_sharding: false
postgres_version: 17
- target_project: large_existing_project
stripe_size: null # cannot re-shared or choose different stripe size for existing, already sharded project
disable_sharding: false
postgres_version: 16
- target_project: new_empty_project_unsharded
stripe_size: null # run with neon defaults which will shard split only when reaching the threshold
disable_sharding: true
postgres_version: 16
max-parallel: 1 # we want to run each stripe size sequentially to be able to compare the results
permissions:
@@ -105,7 +96,6 @@ jobs:
admin_api_key: ${{ secrets.NEON_STAGING_ADMIN_API_KEY }}
shard_count: 8
stripe_size: ${{ matrix.stripe_size }}
disable_sharding: ${{ matrix.disable_sharding }}
- name: Initialize Neon project
if: ${{ startsWith(matrix.target_project, 'new_empty_project') }}

View File

@@ -33,6 +33,10 @@ concurrency:
# No permission for GITHUB_TOKEN by default; the **minimal required** set of permissions should be granted in each job.
permissions: {}
env:
FROM_TAG: ${{ inputs.from-tag }}
TO_TAG: pinned
jobs:
check-manifests:
runs-on: ubuntu-22.04
@@ -42,14 +46,11 @@ jobs:
steps:
- name: Check if we really need to pin the image
id: check-manifests
env:
FROM_TAG: ${{ inputs.from-tag }}
TO_TAG: pinned
run: |
docker manifest inspect "docker.io/neondatabase/build-tools:${FROM_TAG}" > "${FROM_TAG}.json"
docker manifest inspect "docker.io/neondatabase/build-tools:${TO_TAG}" > "${TO_TAG}.json"
docker manifest inspect neondatabase/build-tools:${FROM_TAG} > ${FROM_TAG}.json
docker manifest inspect neondatabase/build-tools:${TO_TAG} > ${TO_TAG}.json
if diff "${FROM_TAG}.json" "${TO_TAG}.json"; then
if diff ${FROM_TAG}.json ${TO_TAG}.json; then
skip=true
else
skip=false
@@ -63,36 +64,55 @@ jobs:
# use format(..) to catch both inputs.force = true AND inputs.force = 'true'
if: needs.check-manifests.outputs.skip == 'false' || format('{0}', inputs.force) == 'true'
permissions:
id-token: write # Required for aws/azure login
packages: write # required for pushing to GHCR
runs-on: ubuntu-22.04
uses: ./.github/workflows/_push-to-container-registry.yml
with:
image-map: |
{
"docker.io/neondatabase/build-tools:${{ inputs.from-tag }}-bullseye": [
"docker.io/neondatabase/build-tools:pinned-bullseye",
"ghcr.io/neondatabase/build-tools:pinned-bullseye",
"${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}.dkr.ecr.${{ vars.AWS_ECR_REGION }}.amazonaws.com/build-tools:pinned-bullseye",
"${{ vars.AZURE_DEV_REGISTRY_NAME }}.azurecr.io/neondatabase/build-tools:pinned-bullseye"
],
"docker.io/neondatabase/build-tools:${{ inputs.from-tag }}-bookworm": [
"docker.io/neondatabase/build-tools:pinned-bookworm",
"docker.io/neondatabase/build-tools:pinned",
"ghcr.io/neondatabase/build-tools:pinned-bookworm",
"ghcr.io/neondatabase/build-tools:pinned",
"${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}.dkr.ecr.${{ vars.AWS_ECR_REGION }}.amazonaws.com/build-tools:pinned-bookworm",
"${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}.dkr.ecr.${{ vars.AWS_ECR_REGION }}.amazonaws.com/build-tools:pinned",
"${{ vars.AZURE_DEV_REGISTRY_NAME }}.azurecr.io/neondatabase/build-tools:pinned-bookworm",
"${{ vars.AZURE_DEV_REGISTRY_NAME }}.azurecr.io/neondatabase/build-tools:pinned"
]
}
aws-region: ${{ vars.AWS_ECR_REGION }}
aws-account-id: "${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}"
aws-role-to-assume: "gha-oidc-neon-admin"
azure-client-id: ${{ vars.AZURE_DEV_CLIENT_ID }}
azure-subscription-id: ${{ vars.AZURE_DEV_SUBSCRIPTION_ID }}
azure-tenant-id: ${{ vars.AZURE_TENANT_ID }}
acr-registry-name: ${{ vars.AZURE_DEV_REGISTRY_NAME }}
secrets: inherit
permissions:
id-token: write # for `azure/login` and aws auth
steps:
- uses: docker/login-action@v3
with:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
- 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
- name: Azure login
uses: azure/login@6c251865b4e6290e7b78be643ea2d005bc51f69a # @v2.1.1
with:
client-id: ${{ secrets.AZURE_DEV_CLIENT_ID }}
tenant-id: ${{ secrets.AZURE_TENANT_ID }}
subscription-id: ${{ secrets.AZURE_DEV_SUBSCRIPTION_ID }}
- name: Login to ACR
run: |
az acr login --name=neoneastus2
- name: Tag build-tools with `${{ env.TO_TAG }}` in Docker Hub, ECR, and ACR
env:
DEFAULT_DEBIAN_VERSION: bookworm
run: |
for debian_version in bullseye bookworm; do
tags=()
tags+=("-t" "neondatabase/build-tools:${TO_TAG}-${debian_version}")
tags+=("-t" "369495373322.dkr.ecr.eu-central-1.amazonaws.com/build-tools:${TO_TAG}-${debian_version}")
tags+=("-t" "neoneastus2.azurecr.io/neondatabase/build-tools:${TO_TAG}-${debian_version}")
if [ "${debian_version}" == "${DEFAULT_DEBIAN_VERSION}" ]; then
tags+=("-t" "neondatabase/build-tools:${TO_TAG}")
tags+=("-t" "369495373322.dkr.ecr.eu-central-1.amazonaws.com/build-tools:${TO_TAG}")
tags+=("-t" "neoneastus2.azurecr.io/neondatabase/build-tools:${TO_TAG}")
fi
docker buildx imagetools create "${tags[@]}" \
neondatabase/build-tools:${FROM_TAG}-${debian_version}
done

View File

@@ -1,41 +0,0 @@
name: Regenerate Postgres Settings
on:
pull_request:
types:
- opened
- synchronize
- reopened
paths:
- pgxn/neon/**.c
- vendor/postgres-v*
- vendor/revisions.json
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref }}
cancel-in-progress: true
permissions:
pull-requests: write
jobs:
regenerate-pg-settings:
runs-on: ubuntu-22.04
steps:
- name: Add comment
uses: thollander/actions-comment-pull-request@v3
with:
comment-tag: ${{ github.job }}
pr-number: ${{ github.event.number }}
message: |
If this PR added a GUC in the Postgres fork or `neon` extension,
please regenerate the Postgres settings in the `cloud` repo:
```
make NEON_WORKDIR=path/to/neon/checkout \
-C goapp/internal/shareddomain/postgres generate
```
If you're an external contributor, a Neon employee will assist in
making sure this step is done.

View File

@@ -88,7 +88,7 @@ jobs:
BUILD_AND_TEST_RUN_ID=${TAG}
while true; do
gh run --repo ${GITHUB_REPOSITORY} view ${BUILD_AND_TEST_RUN_ID} --json jobs --jq '[.jobs[] | select((.name | startswith("push-neon-image-dev")) or (.name | startswith("push-compute-image-dev"))) | {"name": .name, "conclusion": .conclusion, "url": .url}]' > jobs.json
if [ $(jq '[.[] | select(.conclusion == "success")] | length' jobs.json) -eq 2 ]; then
if [ $(jq '[.[] | select(.conclusion == "success")]' jobs.json) -eq 2 ]; then
break
fi
jq -c '.[]' jobs.json | while read -r job; do

72
Cargo.lock generated
View File

@@ -786,7 +786,7 @@ dependencies = [
[[package]]
name = "azure_core"
version = "0.21.0"
source = "git+https://github.com/neondatabase/azure-sdk-for-rust.git?branch=neon#f64bd57262ced51afce5d8909c06dcb11a6dd85a"
source = "git+https://github.com/neondatabase/azure-sdk-for-rust.git?branch=neon#c36ed4c039bb3d59b5a1705f2cc337636c73b541"
dependencies = [
"async-trait",
"base64 0.22.1",
@@ -815,7 +815,7 @@ dependencies = [
[[package]]
name = "azure_identity"
version = "0.21.0"
source = "git+https://github.com/neondatabase/azure-sdk-for-rust.git?branch=neon#f64bd57262ced51afce5d8909c06dcb11a6dd85a"
source = "git+https://github.com/neondatabase/azure-sdk-for-rust.git?branch=neon#c36ed4c039bb3d59b5a1705f2cc337636c73b541"
dependencies = [
"async-lock",
"async-trait",
@@ -834,7 +834,7 @@ dependencies = [
[[package]]
name = "azure_storage"
version = "0.21.0"
source = "git+https://github.com/neondatabase/azure-sdk-for-rust.git?branch=neon#f64bd57262ced51afce5d8909c06dcb11a6dd85a"
source = "git+https://github.com/neondatabase/azure-sdk-for-rust.git?branch=neon#c36ed4c039bb3d59b5a1705f2cc337636c73b541"
dependencies = [
"RustyXML",
"async-lock",
@@ -852,7 +852,7 @@ dependencies = [
[[package]]
name = "azure_storage_blobs"
version = "0.21.0"
source = "git+https://github.com/neondatabase/azure-sdk-for-rust.git?branch=neon#f64bd57262ced51afce5d8909c06dcb11a6dd85a"
source = "git+https://github.com/neondatabase/azure-sdk-for-rust.git?branch=neon#c36ed4c039bb3d59b5a1705f2cc337636c73b541"
dependencies = [
"RustyXML",
"azure_core",
@@ -872,7 +872,7 @@ dependencies = [
[[package]]
name = "azure_svc_blobstorage"
version = "0.21.0"
source = "git+https://github.com/neondatabase/azure-sdk-for-rust.git?branch=neon#f64bd57262ced51afce5d8909c06dcb11a6dd85a"
source = "git+https://github.com/neondatabase/azure-sdk-for-rust.git?branch=neon#c36ed4c039bb3d59b5a1705f2cc337636c73b541"
dependencies = [
"azure_core",
"bytes",
@@ -1029,6 +1029,12 @@ dependencies = [
"generic-array",
]
[[package]]
name = "boxcar"
version = "0.2.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2721c3c5a6f0e7f7e607125d963fedeb765f545f67adc9d71ed934693881eb42"
[[package]]
name = "bstr"
version = "1.5.0"
@@ -1287,7 +1293,6 @@ version = "0.1.0"
dependencies = [
"anyhow",
"chrono",
"jsonwebtoken",
"regex",
"remote_storage",
"serde",
@@ -1303,7 +1308,6 @@ dependencies = [
"aws-config",
"aws-sdk-kms",
"aws-sdk-s3",
"aws-smithy-types",
"axum",
"base64 0.13.1",
"bytes",
@@ -1325,6 +1329,7 @@ dependencies = [
"opentelemetry_sdk",
"postgres",
"postgres_initdb",
"prometheus",
"regex",
"remote_storage",
"reqwest",
@@ -1343,13 +1348,13 @@ dependencies = [
"tower 0.5.2",
"tower-http",
"tracing",
"tracing-opentelemetry",
"tracing-subscriber",
"tracing-utils",
"url",
"utils",
"uuid",
"vm_monitor",
"walkdir",
"workspace_hack",
"zstd",
]
@@ -1546,17 +1551,6 @@ dependencies = [
"itertools 0.10.5",
]
[[package]]
name = "cron"
version = "0.15.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5877d3fbf742507b66bc2a1945106bd30dd8504019d596901ddd012a4dd01740"
dependencies = [
"chrono",
"once_cell",
"winnow",
]
[[package]]
name = "crossbeam-channel"
version = "0.5.8"
@@ -1885,12 +1879,6 @@ dependencies = [
"syn 2.0.90",
]
[[package]]
name = "difflib"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6184e33543162437515c2e2b48714794e37845ec9851711914eec9d308f6ebe8"
[[package]]
name = "digest"
version = "0.10.7"
@@ -3348,17 +3336,6 @@ dependencies = [
"wasm-bindgen",
]
[[package]]
name = "json-structural-diff"
version = "0.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e878e36a8a44c158505c2c818abdc1350413ad83dcb774a0459f6a7ef2b65cbf"
dependencies = [
"difflib",
"regex",
"serde_json",
]
[[package]]
name = "jsonwebtoken"
version = "9.2.0"
@@ -4183,6 +4160,7 @@ dependencies = [
"pageserver_client",
"pageserver_compaction",
"pin-project-lite",
"postgres",
"postgres-protocol",
"postgres-types",
"postgres_backend",
@@ -4269,6 +4247,7 @@ dependencies = [
"futures",
"http-utils",
"pageserver_api",
"postgres",
"reqwest",
"serde",
"thiserror 1.0.69",
@@ -4683,6 +4662,7 @@ dependencies = [
"anyhow",
"itertools 0.10.5",
"once_cell",
"postgres",
"tokio-postgres",
"url",
]
@@ -4947,6 +4927,7 @@ dependencies = [
"aws-sdk-iam",
"aws-sigv4",
"base64 0.13.1",
"boxcar",
"bstr",
"bytes",
"camino",
@@ -4998,6 +4979,7 @@ dependencies = [
"postgres-protocol2",
"postgres_backend",
"pq_proto",
"prometheus",
"rand 0.8.5",
"rand_distr",
"rcgen",
@@ -5022,6 +5004,7 @@ dependencies = [
"smallvec",
"smol_str",
"socket2",
"strum",
"strum_macros",
"subtle",
"thiserror 1.0.69",
@@ -5036,6 +5019,7 @@ dependencies = [
"tracing",
"tracing-log",
"tracing-opentelemetry",
"tracing-serde",
"tracing-subscriber",
"tracing-utils",
"try-lock",
@@ -5824,6 +5808,7 @@ dependencies = [
"once_cell",
"pageserver_api",
"parking_lot 0.12.1",
"postgres",
"postgres-protocol",
"postgres_backend",
"postgres_ffi",
@@ -6457,7 +6442,6 @@ dependencies = [
"chrono",
"clap",
"control_plane",
"cron",
"diesel",
"diesel-async",
"diesel_migrations",
@@ -6468,7 +6452,6 @@ dependencies = [
"humantime",
"hyper 0.14.30",
"itertools 0.10.5",
"json-structural-diff",
"lasso",
"measured",
"metrics",
@@ -6477,13 +6460,10 @@ dependencies = [
"pageserver_client",
"postgres_connection",
"rand 0.8.5",
"regex",
"reqwest",
"routerify",
"rustls 0.23.18",
"rustls-native-certs 0.8.0",
"safekeeper_api",
"safekeeper_client",
"scoped-futures",
"scopeguard",
"serde",
@@ -6491,7 +6471,6 @@ dependencies = [
"strum",
"strum_macros",
"thiserror 1.0.69",
"tikv-jemallocator",
"tokio",
"tokio-postgres",
"tokio-postgres-rustls",
@@ -7045,11 +7024,14 @@ dependencies = [
name = "tokio-postgres2"
version = "0.1.0"
dependencies = [
"async-trait",
"byteorder",
"bytes",
"fallible-iterator",
"futures-util",
"log",
"parking_lot 0.12.1",
"percent-encoding",
"phf",
"pin-project-lite",
"postgres-protocol2",
@@ -7636,13 +7618,13 @@ dependencies = [
"hex",
"hex-literal",
"humantime",
"inferno 0.12.0",
"jsonwebtoken",
"metrics",
"nix 0.27.1",
"once_cell",
"pin-project-lite",
"postgres_connection",
"pprof",
"pq_proto",
"rand 0.8.5",
"regex",
@@ -8150,9 +8132,9 @@ checksum = "589f6da84c646204747d1270a2a5661ea66ed1cced2631d546fdfb155959f9ec"
[[package]]
name = "winnow"
version = "0.6.26"
version = "0.6.13"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1e90edd2ac1aa278a5c4599b1d89cf03074b610800f866d4026dc199d7929a28"
checksum = "59b5e5f6c299a3c7890b876a2a587f3115162487e704907d9b6cd29473052ba1"
dependencies = [
"memchr",
]

View File

@@ -77,7 +77,6 @@ byteorder = "1.4"
bytes = "1.9"
camino = "1.1.6"
cfg-if = "1.0.0"
cron = "0.15"
chrono = { version = "0.4", default-features = false, features = ["clock"] }
clap = { version = "4.0", features = ["derive", "env"] }
clashmap = { version = "1.0", features = ["raw-api"] }
@@ -211,7 +210,6 @@ rustls-native-certs = "0.8"
x509-parser = "0.16"
whoami = "1.5.1"
zerocopy = { version = "0.7", features = ["derive"] }
json-structural-diff = { version = "0.2.0" }
## TODO replace this with tracing
env_logger = "0.10"

View File

@@ -50,14 +50,6 @@ RUN set -e \
&& rm -rf pg_install/build \
&& tar -C pg_install -czf /home/nonroot/postgres_install.tar.gz .
# Prepare cargo-chef recipe
FROM $REPOSITORY/$IMAGE:$TAG AS plan
WORKDIR /home/nonroot
COPY --chown=nonroot . .
RUN cargo chef prepare --recipe-path recipe.json
# Build neon binaries
FROM $REPOSITORY/$IMAGE:$TAG AS build
WORKDIR /home/nonroot
@@ -71,15 +63,9 @@ COPY --from=pg-build /home/nonroot/pg_install/v16/include/postgresql/server pg_i
COPY --from=pg-build /home/nonroot/pg_install/v17/include/postgresql/server pg_install/v17/include/postgresql/server
COPY --from=pg-build /home/nonroot/pg_install/v16/lib pg_install/v16/lib
COPY --from=pg-build /home/nonroot/pg_install/v17/lib pg_install/v17/lib
COPY --from=plan /home/nonroot/recipe.json recipe.json
ARG ADDITIONAL_RUSTFLAGS=""
RUN set -e \
&& RUSTFLAGS="-Clinker=clang -Clink-arg=-fuse-ld=mold -Clink-arg=-Wl,--no-rosegment -Cforce-frame-pointers=yes ${ADDITIONAL_RUSTFLAGS}" cargo chef cook --locked --release --recipe-path recipe.json
COPY --chown=nonroot . .
ARG ADDITIONAL_RUSTFLAGS
RUN set -e \
&& RUSTFLAGS="-Clinker=clang -Clink-arg=-fuse-ld=mold -Clink-arg=-Wl,--no-rosegment -Cforce-frame-pointers=yes ${ADDITIONAL_RUSTFLAGS}" cargo build \
--bin pg_sni_router \

View File

@@ -292,7 +292,7 @@ WORKDIR /home/nonroot
# Rust
# Please keep the version of llvm (installed above) in sync with rust llvm (`rustc --version --verbose | grep LLVM`)
ENV RUSTC_VERSION=1.85.0
ENV RUSTC_VERSION=1.84.1
ENV RUSTUP_HOME="/home/nonroot/.rustup"
ENV PATH="/home/nonroot/.cargo/bin:${PATH}"
ARG RUSTFILT_VERSION=0.2.1
@@ -300,7 +300,6 @@ ARG CARGO_HAKARI_VERSION=0.9.33
ARG CARGO_DENY_VERSION=0.16.2
ARG CARGO_HACK_VERSION=0.6.33
ARG CARGO_NEXTEST_VERSION=0.9.85
ARG CARGO_CHEF_VERSION=0.1.71
ARG CARGO_DIESEL_CLI_VERSION=2.2.6
RUN curl -sSO https://static.rust-lang.org/rustup/dist/$(uname -m)-unknown-linux-gnu/rustup-init && whoami && \
chmod +x rustup-init && \
@@ -315,7 +314,6 @@ RUN curl -sSO https://static.rust-lang.org/rustup/dist/$(uname -m)-unknown-linux
cargo install cargo-deny --locked --version ${CARGO_DENY_VERSION} && \
cargo install cargo-hack --version ${CARGO_HACK_VERSION} && \
cargo install cargo-nextest --version ${CARGO_NEXTEST_VERSION} && \
cargo install cargo-chef --locked --version ${CARGO_CHEF_VERSION} && \
cargo install diesel_cli --version ${CARGO_DIESEL_CLI_VERSION} \
--features postgres-bundled --no-default-features && \
rm -rf /home/nonroot/.cargo/registry && \

View File

@@ -148,7 +148,7 @@ RUN case $DEBIAN_VERSION in \
apt install --no-install-recommends --no-install-suggests -y \
ninja-build git autoconf automake libtool build-essential bison flex libreadline-dev \
zlib1g-dev libxml2-dev libcurl4-openssl-dev libossp-uuid-dev wget ca-certificates pkg-config libssl-dev \
libicu-dev libxslt1-dev liblz4-dev libzstd-dev zstd curl unzip g++ \
libicu-dev libxslt1-dev liblz4-dev libzstd-dev zstd curl unzip \
$VERSION_INSTALLS \
&& apt clean && rm -rf /var/lib/apt/lists/*
@@ -395,22 +395,15 @@ RUN case "${PG_VERSION:?}" in \
cd plv8-src && \
if [[ "${PG_VERSION:?}" < "v17" ]]; then patch -p1 < /ext-src/plv8-3.1.10.patch; fi
# Step 1: Build the vendored V8 engine. It doesn't depend on PostgreSQL, so use
# 'build-deps' as the base. This enables caching and avoids unnecessary rebuilds.
# (The V8 engine takes a very long time to build)
FROM build-deps AS plv8-build
FROM pg-build AS plv8-build
ARG PG_VERSION
WORKDIR /ext-src/plv8-src
RUN apt update && \
apt install --no-install-recommends --no-install-suggests -y \
ninja-build python3-dev libncurses5 binutils clang \
&& apt clean && rm -rf /var/lib/apt/lists/*
COPY --from=plv8-src /ext-src/ /ext-src/
RUN make DOCKER=1 -j $(getconf _NPROCESSORS_ONLN) v8
# Step 2: Build the PostgreSQL-dependent parts
COPY --from=pg-build /usr/local/pgsql /usr/local/pgsql
ENV PATH="/usr/local/pgsql/bin:$PATH"
COPY --from=plv8-src /ext-src/ /ext-src/
WORKDIR /ext-src/plv8-src
RUN \
# generate and copy upgrade scripts
make generate_upgrades && \
@@ -1458,11 +1451,9 @@ RUN make -j $(getconf _NPROCESSORS_ONLN) && \
FROM build-deps AS pg_mooncake-src
ARG PG_VERSION
WORKDIR /ext-src
COPY compute/patches/duckdb_v113.patch .
RUN wget https://github.com/Mooncake-Labs/pg_mooncake/releases/download/v0.1.2/pg_mooncake-0.1.2.tar.gz -O pg_mooncake.tar.gz && \
echo "4550473784fcdd2e1e18062bc01eb9c286abd27cdf5e11a4399be6c0a426ba90 pg_mooncake.tar.gz" | sha256sum --check && \
mkdir pg_mooncake-src && cd pg_mooncake-src && tar xzf ../pg_mooncake.tar.gz --strip-components=1 -C . && \
cd third_party/duckdb && patch -p1 < /ext-src/duckdb_v113.patch && cd ../.. && \
echo "make -f pg_mooncake-src/Makefile.build installcheck TEST_DIR=./test SQL_DIR=./sql SRC_DIR=./src" > neon-test.sh && \
chmod a+x neon-test.sh
@@ -1473,34 +1464,6 @@ RUN make release -j $(getconf _NPROCESSORS_ONLN) && \
make install -j $(getconf _NPROCESSORS_ONLN) && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/pg_mooncake.control
#########################################################################################
#
# Layer "pg-duckdb-pg-build"
# compile pg_duckdb extension
#
#########################################################################################
FROM build-deps AS pg_duckdb-src
WORKDIR /ext-src
COPY compute/patches/pg_duckdb_v031.patch .
COPY compute/patches/duckdb_v120.patch .
# pg_duckdb build requires source dir to be a git repo to get submodules
# allow neon_superuser to execute some functions that in pg_duckdb are available to superuser only:
# - extension management function duckdb.install_extension()
# - access to duckdb.extensions table and its sequence
RUN git clone --depth 1 --branch v0.3.1 https://github.com/duckdb/pg_duckdb.git pg_duckdb-src && \
cd pg_duckdb-src && \
git submodule update --init --recursive && \
patch -p1 < /ext-src/pg_duckdb_v031.patch && \
cd third_party/duckdb && \
patch -p1 < /ext-src/duckdb_v120.patch
FROM pg-build AS pg_duckdb-build
ARG PG_VERSION
COPY --from=pg_duckdb-src /ext-src/ /ext-src/
WORKDIR /ext-src/pg_duckdb-src
RUN make install -j $(getconf _NPROCESSORS_ONLN) && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/pg_duckdb.control
#########################################################################################
#
# Layer "pg_repack"
@@ -1521,73 +1484,6 @@ WORKDIR /ext-src/pg_repack-src
RUN make -j $(getconf _NPROCESSORS_ONLN) && \
make -j $(getconf _NPROCESSORS_ONLN) install
#########################################################################################
#
# Layer "pgaudit"
# compile pgaudit extension
#
#########################################################################################
FROM build-deps AS pgaudit-src
ARG PG_VERSION
WORKDIR /ext-src
RUN case "${PG_VERSION}" in \
"v14") \
export PGAUDIT_VERSION=1.6.2 \
export PGAUDIT_CHECKSUM=1f350d70a0cbf488c0f2b485e3a5c9b11f78ad9e3cbb95ef6904afa1eb3187eb \
;; \
"v15") \
export PGAUDIT_VERSION=1.7.0 \
export PGAUDIT_CHECKSUM=8f4a73e451c88c567e516e6cba7dc1e23bc91686bb6f1f77f8f3126d428a8bd8 \
;; \
"v16") \
export PGAUDIT_VERSION=16.0 \
export PGAUDIT_CHECKSUM=d53ef985f2d0b15ba25c512c4ce967dce07b94fd4422c95bd04c4c1a055fe738 \
;; \
"v17") \
export PGAUDIT_VERSION=17.0 \
export PGAUDIT_CHECKSUM=7d0d08d030275d525f36cd48b38c6455f1023da863385badff0cec44965bfd8c \
;; \
*) \
echo "pgaudit is not supported on this PostgreSQL version" && exit 1;; \
esac && \
wget https://github.com/pgaudit/pgaudit/archive/refs/tags/${PGAUDIT_VERSION}.tar.gz -O pgaudit.tar.gz && \
echo "${PGAUDIT_CHECKSUM} pgaudit.tar.gz" | sha256sum --check && \
mkdir pgaudit-src && cd pgaudit-src && tar xzf ../pgaudit.tar.gz --strip-components=1 -C .
FROM pg-build AS pgaudit-build
COPY --from=pgaudit-src /ext-src/ /ext-src/
WORKDIR /ext-src/pgaudit-src
RUN make install USE_PGXS=1 -j $(getconf _NPROCESSORS_ONLN)
#########################################################################################
#
# Layer "pgauditlogtofile"
# compile pgauditlogtofile extension
#
#########################################################################################
FROM build-deps AS pgauditlogtofile-src
ARG PG_VERSION
WORKDIR /ext-src
RUN case "${PG_VERSION}" in \
"v14" | "v15" | "v16" | "v17") \
export PGAUDITLOGTOFILE_VERSION=v1.6.4 \
export PGAUDITLOGTOFILE_CHECKSUM=ef801eb09c26aaa935c0dabd92c81eb9ebe338930daa9674d420a280c6bc2d70 \
;; \
*) \
echo "pgauditlogtofile is not supported on this PostgreSQL version" && exit 1;; \
esac && \
wget https://github.com/fmbiete/pgauditlogtofile/archive/refs/tags/${PGAUDITLOGTOFILE_VERSION}.tar.gz -O pgauditlogtofile.tar.gz && \
echo "${PGAUDITLOGTOFILE_CHECKSUM} pgauditlogtofile.tar.gz" | sha256sum --check && \
mkdir pgauditlogtofile-src && cd pgauditlogtofile-src && tar xzf ../pgauditlogtofile.tar.gz --strip-components=1 -C .
FROM pg-build AS pgauditlogtofile-build
COPY --from=pgauditlogtofile-src /ext-src/ /ext-src/
WORKDIR /ext-src/pgauditlogtofile-src
RUN make install USE_PGXS=1 -j $(getconf _NPROCESSORS_ONLN)
#########################################################################################
#
# Layer "neon-ext-build"
@@ -1681,10 +1577,7 @@ COPY --from=pg_anon-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=pg_ivm-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=pg_partman-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=pg_mooncake-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=pg_duckdb-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=pg_repack-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=pgaudit-build /usr/local/pgsql/ /usr/local/pgsql/
COPY --from=pgauditlogtofile-build /usr/local/pgsql/ /usr/local/pgsql/
#########################################################################################
#
@@ -1776,6 +1669,29 @@ RUN if [ "$TARGETARCH" = "amd64" ]; then\
&& echo "${pgbouncer_exporter_sha256} pgbouncer_exporter" | sha256sum -c -\
&& echo "${sql_exporter_sha256} sql_exporter" | sha256sum -c -
#########################################################################################
#
# Layer "awscli"
#
#########################################################################################
FROM build-deps AS awscli
ARG TARGETARCH
RUN set -ex; \
if [ "${TARGETARCH}" = "amd64" ]; then \
TARGETARCH_ALT="x86_64"; \
CHECKSUM="c9a9df3770a3ff9259cb469b6179e02829687a464e0824d5c32d378820b53a00"; \
elif [ "${TARGETARCH}" = "arm64" ]; then \
TARGETARCH_ALT="aarch64"; \
CHECKSUM="8181730be7891582b38b028112e81b4899ca817e8c616aad807c9e9d1289223a"; \
else \
echo "Unsupported architecture: ${TARGETARCH}"; exit 1; \
fi; \
curl --retry 5 -L "https://awscli.amazonaws.com/awscli-exe-linux-${TARGETARCH_ALT}-2.17.5.zip" -o /tmp/awscliv2.zip; \
echo "${CHECKSUM} /tmp/awscliv2.zip" | sha256sum -c -; \
unzip /tmp/awscliv2.zip -d /tmp/awscliv2; \
/tmp/awscliv2/aws/install; \
rm -rf /tmp/awscliv2.zip /tmp/awscliv2
#########################################################################################
#
# Clean up postgres folder before inclusion
@@ -1818,7 +1734,7 @@ RUN make PG_VERSION="${PG_VERSION:?}" -C compute
FROM pg-build AS extension-tests
ARG PG_VERSION
COPY docker-compose/ext-src/ /ext-src/
RUN mkdir /ext-src
COPY --from=pg-build /postgres /postgres
#COPY --from=postgis-src /ext-src/ /ext-src/
@@ -1834,7 +1750,7 @@ COPY --from=pg_graphql-src /ext-src/ /ext-src/
COPY --from=hypopg-src /ext-src/ /ext-src/
COPY --from=pg_hashids-src /ext-src/ /ext-src/
COPY --from=rum-src /ext-src/ /ext-src/
COPY --from=pgtap-src /ext-src/ /ext-src/
#COPY --from=pgtap-src /ext-src/ /ext-src/
COPY --from=ip4r-src /ext-src/ /ext-src/
COPY --from=prefix-src /ext-src/ /ext-src/
COPY --from=hll-src /ext-src/ /ext-src/
@@ -1856,20 +1772,14 @@ COPY --from=pg_semver-src /ext-src/ /ext-src/
COPY --from=pg_ivm-src /ext-src/ /ext-src/
COPY --from=pg_partman-src /ext-src/ /ext-src/
#COPY --from=pg_mooncake-src /ext-src/ /ext-src/
COPY --from=pg_repack-src /ext-src/ /ext-src/
COPY --from=pg_repack-build /usr/local/pgsql/ /usr/local/pgsql/
COPY compute/patches/pg_repack.patch /ext-src
RUN cd /ext-src/pg_repack-src && patch -p1 </ext-src/pg_repack.patch && rm -f /ext-src/pg_repack.patch
#COPY --from=pg_repack-src /ext-src/ /ext-src/
COPY --chmod=755 docker-compose/run-tests.sh /run-tests.sh
RUN apt-get update && apt-get install -y libtap-parser-sourcehandler-pgtap-perl\
&& apt clean && rm -rf /ext-src/*.tar.gz /var/lib/apt/lists/*
ENV PATH=/usr/local/pgsql/bin:$PATH
ENV PGHOST=compute
ENV PGPORT=55433
ENV PGUSER=cloud_admin
ENV PGDATABASE=postgres
ENV PG_VERSION=${PG_VERSION:?}
#########################################################################################
#
@@ -1951,6 +1861,9 @@ RUN mkdir /var/db && useradd -m -d /var/db/postgres postgres && \
mkdir /usr/local/download_extensions && \
chown -R postgres:postgres /usr/local/download_extensions
# aws cli is used by fast_import
COPY --from=awscli /usr/local/aws-cli /usr/local/aws-cli
# pgbouncer and its config
COPY --from=pgbouncer /usr/local/pgbouncer/bin/pgbouncer /usr/local/bin/pgbouncer
COPY --chmod=0666 --chown=postgres compute/etc/pgbouncer.ini /etc/pgbouncer.ini

View File

@@ -1,25 +0,0 @@
diff --git a/libduckdb.map b/libduckdb.map
new file mode 100644
index 0000000000..3b56f00cd7
--- /dev/null
+++ b/libduckdb.map
@@ -0,0 +1,6 @@
+DUCKDB_1.1.3 {
+ global:
+ *duckdb*;
+ local:
+ *;
+};
diff --git a/src/CMakeLists.txt b/src/CMakeLists.txt
index 3e757a4bcc..88ab4005b9 100644
--- a/src/CMakeLists.txt
+++ b/src/CMakeLists.txt
@@ -135,6 +135,8 @@ else()
target_link_libraries(duckdb ${DUCKDB_LINK_LIBS})
link_threads(duckdb)
link_extension_libraries(duckdb)
+ target_link_options(duckdb PRIVATE
+ -Wl,--version-script=${CMAKE_SOURCE_DIR}/libduckdb.map)
add_library(duckdb_static STATIC ${ALL_OBJECT_FILES})
target_link_libraries(duckdb_static ${DUCKDB_LINK_LIBS})

View File

@@ -1,67 +0,0 @@
diff --git a/libduckdb_pg_duckdb.map b/libduckdb_pg_duckdb.map
new file mode 100644
index 0000000000..0872978b48
--- /dev/null
+++ b/libduckdb_pg_duckdb.map
@@ -0,0 +1,6 @@
+DUCKDB_1.2.0 {
+ global:
+ *duckdb*;
+ local:
+ *;
+};
diff --git a/src/CMakeLists.txt b/src/CMakeLists.txt
index 58adef3fc0..2c522f91be 100644
--- a/src/CMakeLists.txt
+++ b/src/CMakeLists.txt
@@ -59,7 +59,7 @@ endfunction()
if(AMALGAMATION_BUILD)
- add_library(duckdb SHARED "${PROJECT_SOURCE_DIR}/src/amalgamation/duckdb.cpp")
+ add_library(duckdb_pg_duckdb SHARED "${PROJECT_SOURCE_DIR}/src/amalgamation/duckdb.cpp")
target_link_libraries(duckdb ${DUCKDB_SYSTEM_LIBS})
link_threads(duckdb)
link_extension_libraries(duckdb)
@@ -109,7 +109,7 @@ else()
duckdb_yyjson
duckdb_zstd)
- add_library(duckdb SHARED ${ALL_OBJECT_FILES})
+ add_library(duckdb_pg_duckdb SHARED ${ALL_OBJECT_FILES})
if(WIN32 AND NOT MINGW)
ensure_variable_is_number(DUCKDB_MAJOR_VERSION RC_MAJOR_VERSION)
@@ -131,9 +131,11 @@ else()
target_sources(duckdb PRIVATE version.rc)
endif()
- target_link_libraries(duckdb ${DUCKDB_LINK_LIBS})
- link_threads(duckdb)
- link_extension_libraries(duckdb)
+ target_link_libraries(duckdb_pg_duckdb ${DUCKDB_LINK_LIBS})
+ link_threads(duckdb_pg_duckdb)
+ link_extension_libraries(duckdb_pg_duckdb)
+ target_link_options(duckdb_pg_duckdb PRIVATE
+ -Wl,--version-script=${CMAKE_SOURCE_DIR}/libduckdb_pg_duckdb.map)
add_library(duckdb_static STATIC ${ALL_OBJECT_FILES})
target_link_libraries(duckdb_static ${DUCKDB_LINK_LIBS})
@@ -141,7 +143,7 @@ else()
link_extension_libraries(duckdb_static)
target_include_directories(
- duckdb PUBLIC $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/include>
+ duckdb_pg_duckdb PUBLIC $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/include>
$<INSTALL_INTERFACE:${CMAKE_INSTALL_INCLUDEDIR}>)
target_include_directories(
@@ -161,7 +163,7 @@ else()
endif()
install(
- TARGETS duckdb duckdb_static
+ TARGETS duckdb_pg_duckdb duckdb_static
EXPORT "${DUCKDB_EXPORT_SET}"
LIBRARY DESTINATION "${INSTALL_LIB_DIR}"
ARCHIVE DESTINATION "${INSTALL_LIB_DIR}"

View File

@@ -1,33 +0,0 @@
diff --git a/Makefile b/Makefile
index 3235cc8..6b892bc 100644
--- a/Makefile
+++ b/Makefile
@@ -32,7 +32,7 @@ else
DUCKDB_BUILD_TYPE = release
endif
-DUCKDB_LIB = libduckdb$(DLSUFFIX)
+DUCKDB_LIB = libduckdb_pg_duckdb$(DLSUFFIX)
FULL_DUCKDB_LIB = third_party/duckdb/build/$(DUCKDB_BUILD_TYPE)/src/$(DUCKDB_LIB)
ERROR_ON_WARNING ?=
@@ -54,7 +54,7 @@ override PG_CXXFLAGS += -std=c++17 ${DUCKDB_BUILD_CXX_FLAGS} ${COMPILER_FLAGS} -
# changes to the vendored code in one place.
override PG_CFLAGS += -Wno-declaration-after-statement
-SHLIB_LINK += -Wl,-rpath,$(PG_LIB)/ -lpq -Lthird_party/duckdb/build/$(DUCKDB_BUILD_TYPE)/src -L$(PG_LIB) -lduckdb -lstdc++ -llz4
+SHLIB_LINK += -Wl,-rpath,$(PG_LIB)/ -lpq -Lthird_party/duckdb/build/$(DUCKDB_BUILD_TYPE)/src -L$(PG_LIB) -lduckdb_pg_duckdb -lstdc++ -llz4
include Makefile.global
diff --git a/sql/pg_duckdb--0.2.0--0.3.0.sql b/sql/pg_duckdb--0.2.0--0.3.0.sql
index d777d76..af60106 100644
--- a/sql/pg_duckdb--0.2.0--0.3.0.sql
+++ b/sql/pg_duckdb--0.2.0--0.3.0.sql
@@ -1056,3 +1056,6 @@ GRANT ALL ON FUNCTION duckdb.cache(TEXT, TEXT) TO PUBLIC;
GRANT ALL ON FUNCTION duckdb.cache_info() TO PUBLIC;
GRANT ALL ON FUNCTION duckdb.cache_delete(TEXT) TO PUBLIC;
GRANT ALL ON PROCEDURE duckdb.recycle_ddb() TO PUBLIC;
+GRANT ALL ON FUNCTION duckdb.install_extension(TEXT) TO neon_superuser;
+GRANT ALL ON TABLE duckdb.extensions TO neon_superuser;
+GRANT ALL ON SEQUENCE duckdb.extensions_table_seq TO neon_superuser;

View File

@@ -1,72 +0,0 @@
diff --git a/regress/Makefile b/regress/Makefile
index bf6edcb..89b4c7f 100644
--- a/regress/Makefile
+++ b/regress/Makefile
@@ -17,7 +17,7 @@ INTVERSION := $(shell echo $$(($$(echo $(VERSION).0 | sed 's/\([[:digit:]]\{1,\}
# Test suite
#
-REGRESS := init-extension repack-setup repack-run error-on-invalid-idx no-error-on-invalid-idx after-schema repack-check nosuper tablespace get_order_by trigger
+REGRESS := init-extension repack-setup repack-run error-on-invalid-idx no-error-on-invalid-idx after-schema repack-check nosuper get_order_by trigger
USE_PGXS = 1 # use pgxs if not in contrib directory
PGXS := $(shell $(PG_CONFIG) --pgxs)
diff --git a/regress/expected/nosuper.out b/regress/expected/nosuper.out
index 8d0a94e..63b68bf 100644
--- a/regress/expected/nosuper.out
+++ b/regress/expected/nosuper.out
@@ -4,22 +4,22 @@
SET client_min_messages = error;
DROP ROLE IF EXISTS nosuper;
SET client_min_messages = warning;
-CREATE ROLE nosuper WITH LOGIN;
+CREATE ROLE nosuper WITH LOGIN PASSWORD 'NoSuPeRpAsSwOrD';
-- => OK
\! pg_repack --dbname=contrib_regression --table=tbl_cluster --no-superuser-check
INFO: repacking table "public.tbl_cluster"
-- => ERROR
-\! pg_repack --dbname=contrib_regression --table=tbl_cluster --username=nosuper
+\! PGPASSWORD=NoSuPeRpAsSwOrD pg_repack --dbname=contrib_regression --table=tbl_cluster --username=nosuper
ERROR: pg_repack failed with error: You must be a superuser to use pg_repack
-- => ERROR
-\! pg_repack --dbname=contrib_regression --table=tbl_cluster --username=nosuper --no-superuser-check
+\! PGPASSWORD=NoSuPeRpAsSwOrD pg_repack --dbname=contrib_regression --table=tbl_cluster --username=nosuper --no-superuser-check
ERROR: pg_repack failed with error: ERROR: permission denied for schema repack
LINE 1: select repack.version(), repack.version_sql()
^
GRANT ALL ON ALL TABLES IN SCHEMA repack TO nosuper;
GRANT USAGE ON SCHEMA repack TO nosuper;
-- => ERROR
-\! pg_repack --dbname=contrib_regression --table=tbl_cluster --username=nosuper --no-superuser-check
+\! PGPASSWORD=NoSuPeRpAsSwOrD pg_repack --dbname=contrib_regression --table=tbl_cluster --username=nosuper --no-superuser-check
INFO: repacking table "public.tbl_cluster"
ERROR: query failed: ERROR: current transaction is aborted, commands ignored until end of transaction block
DETAIL: query was: RESET lock_timeout
diff --git a/regress/sql/nosuper.sql b/regress/sql/nosuper.sql
index 072f0fa..dbe60f8 100644
--- a/regress/sql/nosuper.sql
+++ b/regress/sql/nosuper.sql
@@ -4,19 +4,19 @@
SET client_min_messages = error;
DROP ROLE IF EXISTS nosuper;
SET client_min_messages = warning;
-CREATE ROLE nosuper WITH LOGIN;
+CREATE ROLE nosuper WITH LOGIN PASSWORD 'NoSuPeRpAsSwOrD';
-- => OK
\! pg_repack --dbname=contrib_regression --table=tbl_cluster --no-superuser-check
-- => ERROR
-\! pg_repack --dbname=contrib_regression --table=tbl_cluster --username=nosuper
+\! PGPASSWORD=NoSuPeRpAsSwOrD pg_repack --dbname=contrib_regression --table=tbl_cluster --username=nosuper
-- => ERROR
-\! pg_repack --dbname=contrib_regression --table=tbl_cluster --username=nosuper --no-superuser-check
+\! PGPASSWORD=NoSuPeRpAsSwOrD pg_repack --dbname=contrib_regression --table=tbl_cluster --username=nosuper --no-superuser-check
GRANT ALL ON ALL TABLES IN SCHEMA repack TO nosuper;
GRANT USAGE ON SCHEMA repack TO nosuper;
-- => ERROR
-\! pg_repack --dbname=contrib_regression --table=tbl_cluster --username=nosuper --no-superuser-check
+\! PGPASSWORD=NoSuPeRpAsSwOrD pg_repack --dbname=contrib_regression --table=tbl_cluster --username=nosuper --no-superuser-check
REVOKE ALL ON ALL TABLES IN SCHEMA repack FROM nosuper;
REVOKE USAGE ON SCHEMA repack FROM nosuper;

View File

@@ -44,11 +44,6 @@ shutdownHook: |
files:
- filename: compute_ctl-sudoers
content: |
# Reverse hostname lookup doesn't currently work, and isn't needed anyway when all
# the rules use ALL as the hostname. Avoid the pointless lookups and the "unable to
# resolve host" log messages that they generate.
Defaults !fqdn
# Allow postgres user (which is what compute_ctl runs as) to run /neonvm/bin/resize-swap
# and /neonvm/bin/set-disk-quota as root without requiring entering a password (NOPASSWD),
# regardless of hostname (ALL)

View File

@@ -44,17 +44,10 @@ shutdownHook: |
files:
- filename: compute_ctl-sudoers
content: |
# Reverse hostname lookup doesn't currently work, and isn't needed anyway when all
# the rules use ALL as the hostname. Avoid the pointless lookups and the "unable to
# resolve host" log messages that they generate.
Defaults !fqdn
# Allow postgres user (which is what compute_ctl runs as) to run /neonvm/bin/resize-swap
# and /neonvm/bin/set-disk-quota as root without requiring entering a password (NOPASSWD),
# regardless of hostname (ALL)
#
# Also allow it to shut down the VM. The fast_import job does that when it's finished.
postgres ALL=(root) NOPASSWD: /neonvm/bin/resize-swap, /neonvm/bin/set-disk-quota, /neonvm/bin/poweroff
postgres ALL=(root) NOPASSWD: /neonvm/bin/resize-swap, /neonvm/bin/set-disk-quota
- filename: cgconfig.conf
content: |
# Configuration for cgroups in VM compute nodes

View File

@@ -1,7 +1,7 @@
[package]
name = "compute_tools"
version = "0.1.0"
edition = "2024"
edition.workspace = true
license.workspace = true
[features]
@@ -14,7 +14,6 @@ base64.workspace = true
aws-config.workspace = true
aws-sdk-s3.workspace = true
aws-sdk-kms.workspace = true
aws-smithy-types.workspace = true
anyhow.workspace = true
axum = { workspace = true, features = [] }
camino.workspace = true
@@ -47,12 +46,13 @@ tokio-postgres.workspace = true
tokio-util.workspace = true
tokio-stream.workspace = true
tracing.workspace = true
tracing-opentelemetry.workspace = true
tracing-subscriber.workspace = true
tracing-utils.workspace = true
thiserror.workspace = true
url.workspace = true
uuid.workspace = true
walkdir.workspace = true
prometheus.workspace = true
postgres_initdb.workspace = true
compute_api.workspace = true

View File

@@ -40,31 +40,35 @@ use std::path::Path;
use std::process::exit;
use std::str::FromStr;
use std::sync::atomic::Ordering;
use std::sync::{Arc, Condvar, Mutex, RwLock, mpsc};
use std::thread;
use std::time::Duration;
use std::sync::{mpsc, Arc, Condvar, Mutex, RwLock};
use std::time::SystemTime;
use std::{thread, time::Duration};
use anyhow::{Context, Result};
use chrono::Utc;
use clap::Parser;
use compute_api::responses::{ComputeCtlConfig, ComputeStatus};
use compute_tools::disk_quota::set_disk_quota;
use compute_tools::http::server::Server;
use compute_tools::lsn_lease::launch_lsn_lease_bg_task_for_static;
use signal_hook::consts::{SIGQUIT, SIGTERM};
use signal_hook::{consts::SIGINT, iterator::Signals};
use tracing::{error, info, warn};
use url::Url;
use compute_api::responses::ComputeStatus;
use compute_api::spec::ComputeSpec;
use compute_tools::compute::{
ComputeNode, ComputeState, PG_PID, ParsedSpec, forward_termination_signal,
forward_termination_signal, ComputeNode, ComputeState, ParsedSpec, PG_PID,
};
use compute_tools::configurator::launch_configurator;
use compute_tools::extension_server::get_pg_version_string;
use compute_tools::http::server::Server;
use compute_tools::logger::*;
use compute_tools::lsn_lease::launch_lsn_lease_bg_task_for_static;
use compute_tools::monitor::launch_monitor;
use compute_tools::params::*;
use compute_tools::spec::*;
use rlimit::{Resource, setrlimit};
use signal_hook::consts::{SIGINT, SIGQUIT, SIGTERM};
use signal_hook::iterator::Signals;
use tracing::{error, info};
use url::Url;
use compute_tools::swap::resize_swap;
use rlimit::{setrlimit, Resource};
use utils::failpoint_support;
// this is an arbitrary build tag. Fine as a default / for testing purposes
@@ -82,6 +86,19 @@ fn parse_remote_ext_config(arg: &str) -> Result<String> {
}
}
/// Generate a compute ID if one is not supplied. This exists to keep forward
/// compatibility tests working, but will be removed in a future iteration.
fn generate_compute_id() -> String {
let now = SystemTime::now();
format!(
"compute-{}",
now.duration_since(SystemTime::UNIX_EPOCH)
.unwrap()
.as_secs()
)
}
#[derive(Parser)]
#[command(rename_all = "kebab-case")]
struct Cli {
@@ -95,13 +112,16 @@ struct Cli {
/// outside the compute will talk to the compute through this port. Keep
/// the previous name for this argument around for a smoother release
/// with the control plane.
#[arg(long, default_value_t = 3080)]
///
/// TODO: Remove the alias after the control plane release which teaches the
/// control plane about the renamed argument.
#[arg(long, alias = "http-port", default_value_t = 3080)]
pub external_http_port: u16,
/// The port to bind the internal listening HTTP server to. Clients include
/// The port to bind the internal listening HTTP server to. Clients like
/// the neon extension (for installing remote extensions) and local_proxy.
#[arg(long, default_value_t = 3081)]
pub internal_http_port: u16,
#[arg(long)]
pub internal_http_port: Option<u16>,
#[arg(short = 'D', long, value_name = "DATADIR")]
pub pgdata: String,
@@ -136,7 +156,7 @@ struct Cli {
#[arg(short = 'S', long, group = "spec-path")]
pub spec_path: Option<OsString>,
#[arg(short = 'i', long, group = "compute-id")]
#[arg(short = 'i', long, group = "compute-id", default_value = generate_compute_id())]
pub compute_id: String,
#[arg(short = 'p', long, conflicts_with_all = ["spec", "spec-path"], value_name = "CONTROL_PLANE_API_BASE_URL")]
@@ -146,8 +166,6 @@ struct Cli {
fn main() -> Result<()> {
let cli = Cli::parse();
let scenario = failpoint_support::init();
// For historical reasons, the main thread that processes the spec and launches postgres
// is synchronous, but we always have this tokio runtime available and we "enter" it so
// that you can use tokio::spawn() and tokio::runtime::Handle::current().block_on(...)
@@ -159,6 +177,8 @@ fn main() -> Result<()> {
let build_tag = runtime.block_on(init())?;
let scenario = failpoint_support::init();
// enable core dumping for all child processes
setrlimit(Resource::CORE, rlimit::INFINITY, rlimit::INFINITY)?;
@@ -170,11 +190,7 @@ fn main() -> Result<()> {
let compute = wait_spec(build_tag, &cli, cli_spec)?;
bootstrap_compute(
compute,
#[cfg(target_os = "linux")]
&cli,
)
start_postgres(&cli, compute)?
// Startup is finished, exit the startup tracing span
};
@@ -265,7 +281,6 @@ fn try_spec_from_cli(cli: &Cli) -> Result<CliSpecParams> {
info!("got spec from cli argument {}", spec_json);
return Ok(CliSpecParams {
spec: Some(serde_json::from_str(spec_json)?),
compute_ctl_config: ComputeCtlConfig::default(),
live_config_allowed: false,
});
}
@@ -275,7 +290,6 @@ fn try_spec_from_cli(cli: &Cli) -> Result<CliSpecParams> {
let file = File::open(Path::new(spec_path))?;
return Ok(CliSpecParams {
spec: Some(serde_json::from_reader(file)?),
compute_ctl_config: ComputeCtlConfig::default(),
live_config_allowed: true,
});
}
@@ -285,9 +299,8 @@ fn try_spec_from_cli(cli: &Cli) -> Result<CliSpecParams> {
};
match get_spec_from_control_plane(cli.control_plane_uri.as_ref().unwrap(), &cli.compute_id) {
Ok(resp) => Ok(CliSpecParams {
spec: resp.0,
compute_ctl_config: resp.1,
Ok(spec) => Ok(CliSpecParams {
spec,
live_config_allowed: true,
}),
Err(e) => {
@@ -304,8 +317,6 @@ fn try_spec_from_cli(cli: &Cli) -> Result<CliSpecParams> {
struct CliSpecParams {
/// If a spec was provided via CLI or file, the [`ComputeSpec`]
spec: Option<ComputeSpec>,
#[allow(dead_code)]
compute_ctl_config: ComputeCtlConfig,
live_config_allowed: bool,
}
@@ -315,7 +326,6 @@ fn wait_spec(
CliSpecParams {
spec,
live_config_allowed,
compute_ctl_config: _,
}: CliSpecParams,
) -> Result<Arc<ComputeNode>> {
let mut new_state = ComputeState::new();
@@ -343,15 +353,13 @@ fn wait_spec(
pgbin: cli.pgbin.clone(),
pgversion: get_pg_version_string(&cli.pgbin),
external_http_port: cli.external_http_port,
internal_http_port: cli.internal_http_port,
internal_http_port: cli.internal_http_port.unwrap_or(cli.external_http_port + 1),
live_config_allowed,
state: Mutex::new(new_state),
state_changed: Condvar::new(),
ext_remote_storage: cli.remote_ext_config.clone(),
ext_download_progress: RwLock::new(HashMap::new()),
build_tag,
resize_swap_on_bind: cli.resize_swap_on_bind,
set_disk_quota_for_fs: cli.set_disk_quota_for_fs.clone(),
};
let compute = Arc::new(compute_node);
@@ -369,7 +377,7 @@ fn wait_spec(
// The internal HTTP server could be launched later, but there isn't much
// sense in waiting.
Server::Internal(cli.internal_http_port).launch(&compute);
Server::Internal(cli.internal_http_port.unwrap_or(cli.external_http_port + 1)).launch(&compute);
if !spec_set {
// No spec provided, hang waiting for it.
@@ -404,11 +412,10 @@ fn wait_spec(
Ok(compute)
}
// Start Postgres and some aux threads like various monitors
fn bootstrap_compute(
fn start_postgres(
cli: &Cli,
compute: Arc<ComputeNode>,
#[cfg(target_os = "linux")] cli: &Cli,
) -> (Option<PostgresHandle>, StartPostgresResult) {
) -> Result<(Option<PostgresHandle>, StartPostgresResult)> {
// We got all we need, update the state.
let mut state = compute.state.lock().unwrap();
state.set_status(ComputeStatus::Init, &compute.state_changed);
@@ -417,9 +424,10 @@ fn bootstrap_compute(
"running compute with features: {:?}",
state.pspec.as_ref().unwrap().spec.features
);
// Before we release the mutex, fetch some parameters for later.
// 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,
..
@@ -430,86 +438,120 @@ fn bootstrap_compute(
let _monitor_handle = launch_monitor(&compute);
let _configurator_handle = launch_configurator(&compute);
let mut prestartup_failed = false;
let mut delay_exit = false;
// Start Postgres
match compute.start_compute() {
Ok(pg) => {
info!(postmaster_pid = %pg.0.id(), "Postgres was started");
// Start the vm-monitor if directed to. The vm-monitor only runs on linux
// because it requires cgroups.
cfg_if::cfg_if! {
if #[cfg(target_os = "linux")] {
use std::env;
use tokio_util::sync::CancellationToken;
// 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 {
Some(cli.filecache_connstr.clone())
};
let vm_monitor = if env::var_os("AUTOSCALING").is_some() {
let vm_monitor = tokio::spawn(vm_monitor::start(
Box::leak(Box::new(vm_monitor::Args {
cgroup: Some(cli.cgroup.clone()),
pgconnstr,
addr: cli.vm_monitor_addr.clone(),
})),
token.clone(),
));
Some(vm_monitor)
} else {
None
};
}
// Resize swap to the desired size if the compute spec says so
if let (Some(size_bytes), true) = (swap_size_bytes, cli.resize_swap_on_bind) {
// To avoid 'swapoff' hitting postgres startup, we need to run resize-swap to completion
// *before* starting postgres.
//
// In theory, we could do this asynchronously if SkipSwapon was enabled for VMs, but this
// carries a risk of introducing hard-to-debug issues - e.g. if postgres sometimes gets
// OOM-killed during startup because swap wasn't available yet.
match resize_swap(size_bytes) {
Ok(()) => {
let size_mib = size_bytes as f32 / (1 << 20) as f32; // just for more coherent display.
info!(%size_bytes, %size_mib, "resized swap");
}
Err(err) => {
let err = err.context("failed to resize swap");
error!("{err:#}");
(
Some(pg),
StartPostgresResult {
delay_exit,
compute,
#[cfg(target_os = "linux")]
token,
#[cfg(target_os = "linux")]
vm_monitor,
},
)
}
Err(err) => {
error!("could not start the compute node: {:#}", err);
compute.set_failed_status(err);
delay_exit = true;
cfg_if::cfg_if! {
if #[cfg(target_os = "linux")] {
use tokio_util::sync::CancellationToken;
let token = CancellationToken::new();
(
None,
StartPostgresResult {
delay_exit,
compute,
token,
vm_monitor: None,
},
)
} else {
(None, StartPostgresResult {
delay_exit,
compute,
})
}
// Mark compute startup as failed; don't try to start postgres, and report this
// error to the control plane when it next asks.
prestartup_failed = true;
compute.set_failed_status(err);
delay_exit = true;
}
}
}
// Set disk quota if the compute spec says so
if let (Some(disk_quota_bytes), Some(disk_quota_fs_mountpoint)) =
(disk_quota_bytes, cli.set_disk_quota_for_fs.as_ref())
{
match set_disk_quota(disk_quota_bytes, disk_quota_fs_mountpoint) {
Ok(()) => {
let size_mib = disk_quota_bytes as f32 / (1 << 20) as f32; // just for more coherent display.
info!(%disk_quota_bytes, %size_mib, "set disk quota");
}
Err(err) => {
let err = err.context("failed to set disk quota");
error!("{err:#}");
// Mark compute startup as failed; don't try to start postgres, and report this
// error to the control plane when it next asks.
prestartup_failed = true;
compute.set_failed_status(err);
delay_exit = true;
}
}
}
// Start Postgres
let mut pg = None;
if !prestartup_failed {
pg = match compute.start_compute() {
Ok(pg) => {
info!(postmaster_pid = %pg.0.id(), "Postgres was started");
Some(pg)
}
Err(err) => {
error!("could not start the compute node: {:#}", err);
compute.set_failed_status(err);
delay_exit = true;
None
}
};
} else {
warn!("skipping postgres startup because pre-startup step failed");
}
// Start the vm-monitor if directed to. The vm-monitor only runs on linux
// because it requires cgroups.
cfg_if::cfg_if! {
if #[cfg(target_os = "linux")] {
use std::env;
use tokio_util::sync::CancellationToken;
// 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 {
Some(cli.filecache_connstr.clone())
};
let vm_monitor = if env::var_os("AUTOSCALING").is_some() {
let vm_monitor = tokio::spawn(vm_monitor::start(
Box::leak(Box::new(vm_monitor::Args {
cgroup: Some(cli.cgroup.clone()),
pgconnstr,
addr: cli.vm_monitor_addr.clone(),
})),
token.clone(),
));
Some(vm_monitor)
} else {
None
};
}
}
Ok((
pg,
StartPostgresResult {
delay_exit,
compute,
#[cfg(target_os = "linux")]
token,
#[cfg(target_os = "linux")]
vm_monitor,
},
))
}
type PostgresHandle = (std::process::Child, tokio::task::JoinHandle<Result<()>>);

View File

@@ -25,13 +25,13 @@
//! docker push localhost:3030/localregistry/compute-node-v14:latest
//! ```
use anyhow::{Context, bail};
use anyhow::Context;
use aws_config::BehaviorVersion;
use camino::{Utf8Path, Utf8PathBuf};
use clap::{Parser, Subcommand};
use compute_tools::extension_server::{PostgresMajorVersion, get_pg_version};
use clap::Parser;
use compute_tools::extension_server::{get_pg_version, PostgresMajorVersion};
use nix::unistd::Pid;
use tracing::{Instrument, error, info, info_span, warn};
use tracing::{error, info, info_span, warn, Instrument};
use utils::fs_ext::is_directory_empty;
#[path = "fast_import/aws_s3_sync.rs"]
@@ -44,59 +44,32 @@ mod s3_uri;
const PG_WAIT_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(600);
const PG_WAIT_RETRY_INTERVAL: std::time::Duration = std::time::Duration::from_millis(300);
#[derive(Subcommand, Debug)]
enum Command {
/// Runs local postgres (neon binary), restores into it,
/// uploads pgdata to s3 to be consumed by pageservers
Pgdata {
/// Raw connection string to the source database. Used only in tests,
/// real scenario uses encrypted connection string in spec.json from s3.
#[clap(long)]
source_connection_string: Option<String>,
/// If specified, will not shut down the local postgres after the import. Used in local testing
#[clap(short, long)]
interactive: bool,
/// Port to run postgres on. Default is 5432.
#[clap(long, default_value_t = 5432)]
pg_port: u16, // port to run postgres on, 5432 is default
/// Number of CPUs in the system. This is used to configure # of
/// parallel worker processes, for index creation.
#[clap(long, env = "NEON_IMPORTER_NUM_CPUS")]
num_cpus: Option<usize>,
/// Amount of RAM in the system. This is used to configure shared_buffers
/// and maintenance_work_mem.
#[clap(long, env = "NEON_IMPORTER_MEMORY_MB")]
memory_mb: Option<usize>,
},
/// Runs pg_dump-pg_restore from source to destination without running local postgres.
DumpRestore {
/// Raw connection string to the source database. Used only in tests,
/// real scenario uses encrypted connection string in spec.json from s3.
#[clap(long)]
source_connection_string: Option<String>,
/// Raw connection string to the destination database. Used only in tests,
/// real scenario uses encrypted connection string in spec.json from s3.
#[clap(long)]
destination_connection_string: Option<String>,
},
}
#[derive(clap::Parser)]
struct Args {
#[clap(long, env = "NEON_IMPORTER_WORKDIR")]
#[clap(long)]
working_directory: Utf8PathBuf,
#[clap(long, env = "NEON_IMPORTER_S3_PREFIX")]
s3_prefix: Option<s3_uri::S3Uri>,
#[clap(long, env = "NEON_IMPORTER_PG_BIN_DIR")]
#[clap(long)]
source_connection_string: Option<String>,
#[clap(short, long)]
interactive: bool,
#[clap(long)]
pg_bin_dir: Utf8PathBuf,
#[clap(long, env = "NEON_IMPORTER_PG_LIB_DIR")]
#[clap(long)]
pg_lib_dir: Utf8PathBuf,
#[clap(long)]
pg_port: Option<u16>, // port to run postgres on, 5432 is default
#[clap(subcommand)]
command: Command,
/// Number of CPUs in the system. This is used to configure # of
/// parallel worker processes, for index creation.
#[clap(long, env = "NEON_IMPORTER_NUM_CPUS")]
num_cpus: Option<usize>,
/// Amount of RAM in the system. This is used to configure shared_buffers
/// and maintenance_work_mem.
#[clap(long, env = "NEON_IMPORTER_MEMORY_MB")]
memory_mb: Option<usize>,
}
#[serde_with::serde_as]
@@ -105,8 +78,6 @@ struct Spec {
encryption_secret: EncryptionSecret,
#[serde_as(as = "serde_with::base64::Base64")]
source_connstring_ciphertext_base64: Vec<u8>,
#[serde_as(as = "Option<serde_with::base64::Base64>")]
destination_connstring_ciphertext_base64: Option<Vec<u8>>,
}
#[derive(serde::Deserialize)]
@@ -122,150 +93,192 @@ const DEFAULT_LOCALE: &str = if cfg!(target_os = "macos") {
"C.UTF-8"
};
async fn decode_connstring(
kms_client: &aws_sdk_kms::Client,
key_id: &String,
connstring_ciphertext_base64: Vec<u8>,
) -> Result<String, anyhow::Error> {
let mut output = kms_client
.decrypt()
.key_id(key_id)
.ciphertext_blob(aws_sdk_s3::primitives::Blob::new(
connstring_ciphertext_base64,
))
.send()
.await
.context("decrypt connection string")?;
#[tokio::main]
pub(crate) async fn main() -> anyhow::Result<()> {
utils::logging::init(
utils::logging::LogFormat::Plain,
utils::logging::TracingErrorLayerEnablement::EnableWithRustLogFilter,
utils::logging::Output::Stdout,
)?;
let plaintext = output
.plaintext
.take()
.context("get plaintext connection string")?;
info!("starting");
String::from_utf8(plaintext.into_inner()).context("parse connection string as utf8")
}
let args = Args::parse();
struct PostgresProcess {
pgdata_dir: Utf8PathBuf,
pg_bin_dir: Utf8PathBuf,
pgbin: Utf8PathBuf,
pg_lib_dir: Utf8PathBuf,
postgres_proc: Option<tokio::process::Child>,
}
impl PostgresProcess {
fn new(pgdata_dir: Utf8PathBuf, pg_bin_dir: Utf8PathBuf, pg_lib_dir: Utf8PathBuf) -> Self {
Self {
pgdata_dir,
pgbin: pg_bin_dir.join("postgres"),
pg_bin_dir,
pg_lib_dir,
postgres_proc: None,
}
// Validate arguments
if args.s3_prefix.is_none() && args.source_connection_string.is_none() {
anyhow::bail!("either s3_prefix or source_connection_string must be specified");
}
if args.s3_prefix.is_some() && args.source_connection_string.is_some() {
anyhow::bail!("only one of s3_prefix or source_connection_string can be specified");
}
async fn prepare(&self, initdb_user: &str) -> Result<(), anyhow::Error> {
tokio::fs::create_dir(&self.pgdata_dir)
.await
.context("create pgdata directory")?;
let working_directory = args.working_directory;
let pg_bin_dir = args.pg_bin_dir;
let pg_lib_dir = args.pg_lib_dir;
let pg_port = args.pg_port.unwrap_or_else(|| {
info!("pg_port not specified, using default 5432");
5432
});
let pg_version = match get_pg_version(self.pgbin.as_ref()) {
PostgresMajorVersion::V14 => 14,
PostgresMajorVersion::V15 => 15,
PostgresMajorVersion::V16 => 16,
PostgresMajorVersion::V17 => 17,
// Initialize AWS clients only if s3_prefix is specified
let (aws_config, kms_client) = if args.s3_prefix.is_some() {
let config = aws_config::load_defaults(BehaviorVersion::v2024_03_28()).await;
let kms = aws_sdk_kms::Client::new(&config);
(Some(config), Some(kms))
} else {
(None, None)
};
// Get source connection string either from S3 spec or direct argument
let source_connection_string = if let Some(s3_prefix) = &args.s3_prefix {
let spec: Spec = {
let spec_key = s3_prefix.append("/spec.json");
let s3_client = aws_sdk_s3::Client::new(aws_config.as_ref().unwrap());
let object = s3_client
.get_object()
.bucket(&spec_key.bucket)
.key(spec_key.key)
.send()
.await
.context("get spec from s3")?
.body
.collect()
.await
.context("download spec body")?;
serde_json::from_slice(&object.into_bytes()).context("parse spec as json")?
};
postgres_initdb::do_run_initdb(postgres_initdb::RunInitdbArgs {
superuser: initdb_user,
locale: DEFAULT_LOCALE, // XXX: this shouldn't be hard-coded,
pg_version,
initdb_bin: self.pg_bin_dir.join("initdb").as_ref(),
library_search_path: &self.pg_lib_dir, // TODO: is this right? Prob works in compute image, not sure about neon_local.
pgdata: &self.pgdata_dir,
})
match spec.encryption_secret {
EncryptionSecret::KMS { key_id } => {
let mut output = kms_client
.unwrap()
.decrypt()
.key_id(key_id)
.ciphertext_blob(aws_sdk_s3::primitives::Blob::new(
spec.source_connstring_ciphertext_base64,
))
.send()
.await
.context("decrypt source connection string")?;
let plaintext = output
.plaintext
.take()
.context("get plaintext source connection string")?;
String::from_utf8(plaintext.into_inner())
.context("parse source connection string as utf8")?
}
}
} else {
args.source_connection_string.unwrap()
};
match tokio::fs::create_dir(&working_directory).await {
Ok(()) => {}
Err(e) if e.kind() == std::io::ErrorKind::AlreadyExists => {
if !is_directory_empty(&working_directory)
.await
.context("check if working directory is empty")?
{
anyhow::bail!("working directory is not empty");
} else {
// ok
}
}
Err(e) => return Err(anyhow::Error::new(e).context("create working directory")),
}
let pgdata_dir = working_directory.join("pgdata");
tokio::fs::create_dir(&pgdata_dir)
.await
.context("initdb")
}
.context("create pgdata directory")?;
async fn start(
&mut self,
initdb_user: &str,
port: u16,
nproc: usize,
memory_mb: usize,
) -> Result<&tokio::process::Child, anyhow::Error> {
self.prepare(initdb_user).await?;
let pgbin = pg_bin_dir.join("postgres");
let pg_version = match get_pg_version(pgbin.as_ref()) {
PostgresMajorVersion::V14 => 14,
PostgresMajorVersion::V15 => 15,
PostgresMajorVersion::V16 => 16,
PostgresMajorVersion::V17 => 17,
};
let superuser = "cloud_admin"; // XXX: this shouldn't be hard-coded
postgres_initdb::do_run_initdb(postgres_initdb::RunInitdbArgs {
superuser,
locale: DEFAULT_LOCALE, // XXX: this shouldn't be hard-coded,
pg_version,
initdb_bin: pg_bin_dir.join("initdb").as_ref(),
library_search_path: &pg_lib_dir, // TODO: is this right? Prob works in compute image, not sure about neon_local.
pgdata: &pgdata_dir,
})
.await
.context("initdb")?;
// Somewhat arbitrarily, use 10 % of memory for shared buffer cache, 70% for
// maintenance_work_mem (i.e. for sorting during index creation), and leave the rest
// available for misc other stuff that PostgreSQL uses memory for.
let shared_buffers_mb = ((memory_mb as f32) * 0.10) as usize;
let maintenance_work_mem_mb = ((memory_mb as f32) * 0.70) as usize;
// If the caller didn't specify CPU / RAM to use for sizing, default to
// number of CPUs in the system, and pretty arbitrarily, 256 MB of RAM.
let nproc = args.num_cpus.unwrap_or_else(num_cpus::get);
let memory_mb = args.memory_mb.unwrap_or(256);
//
// Launch postgres process
//
let mut proc = tokio::process::Command::new(&self.pgbin)
.arg("-D")
.arg(&self.pgdata_dir)
.args(["-p", &format!("{port}")])
.args(["-c", "wal_level=minimal"])
.args(["-c", &format!("shared_buffers={shared_buffers_mb}MB")])
.args(["-c", "max_wal_senders=0"])
.args(["-c", "fsync=off"])
.args(["-c", "full_page_writes=off"])
.args(["-c", "synchronous_commit=off"])
.args([
"-c",
&format!("maintenance_work_mem={maintenance_work_mem_mb}MB"),
])
.args(["-c", &format!("max_parallel_maintenance_workers={nproc}")])
.args(["-c", &format!("max_parallel_workers={nproc}")])
.args(["-c", &format!("max_parallel_workers_per_gather={nproc}")])
.args(["-c", &format!("max_worker_processes={nproc}")])
.args(["-c", "effective_io_concurrency=100"])
.env_clear()
.env("LD_LIBRARY_PATH", &self.pg_lib_dir)
.env(
"ASAN_OPTIONS",
std::env::var("ASAN_OPTIONS").unwrap_or_default(),
)
.env(
"UBSAN_OPTIONS",
std::env::var("UBSAN_OPTIONS").unwrap_or_default(),
)
.stdout(std::process::Stdio::piped())
.stderr(std::process::Stdio::piped())
.spawn()
.context("spawn postgres")?;
// Somewhat arbitrarily, use 10 % of memory for shared buffer cache, 70% for
// maintenance_work_mem (i.e. for sorting during index creation), and leave the rest
// available for misc other stuff that PostgreSQL uses memory for.
let shared_buffers_mb = ((memory_mb as f32) * 0.10) as usize;
let maintenance_work_mem_mb = ((memory_mb as f32) * 0.70) as usize;
info!("spawned postgres, waiting for it to become ready");
tokio::spawn(
child_stdio_to_log::relay_process_output(proc.stdout.take(), proc.stderr.take())
.instrument(info_span!("postgres")),
);
self.postgres_proc = Some(proc);
Ok(self.postgres_proc.as_ref().unwrap())
}
async fn shutdown(&mut self) -> Result<(), anyhow::Error> {
let proc: &mut tokio::process::Child = self.postgres_proc.as_mut().unwrap();
info!("shutdown postgres");
nix::sys::signal::kill(
Pid::from_raw(i32::try_from(proc.id().unwrap()).expect("convert child pid to i32")),
nix::sys::signal::SIGTERM,
//
// Launch postgres process
//
let mut postgres_proc = tokio::process::Command::new(pgbin)
.arg("-D")
.arg(&pgdata_dir)
.args(["-p", &format!("{pg_port}")])
.args(["-c", "wal_level=minimal"])
.args(["-c", &format!("shared_buffers={shared_buffers_mb}MB")])
.args(["-c", "max_wal_senders=0"])
.args(["-c", "fsync=off"])
.args(["-c", "full_page_writes=off"])
.args(["-c", "synchronous_commit=off"])
.args([
"-c",
&format!("maintenance_work_mem={maintenance_work_mem_mb}MB"),
])
.args(["-c", &format!("max_parallel_maintenance_workers={nproc}")])
.args(["-c", &format!("max_parallel_workers={nproc}")])
.args(["-c", &format!("max_parallel_workers_per_gather={nproc}")])
.args(["-c", &format!("max_worker_processes={nproc}")])
.args([
"-c",
&format!(
"effective_io_concurrency={}",
if cfg!(target_os = "macos") { 0 } else { 100 }
),
])
.env_clear()
.env("LD_LIBRARY_PATH", &pg_lib_dir)
.env(
"ASAN_OPTIONS",
std::env::var("ASAN_OPTIONS").unwrap_or_default(),
)
.context("signal postgres to shut down")?;
proc.wait()
.await
.context("wait for postgres to shut down")
.map(|_| ())
}
}
.env(
"UBSAN_OPTIONS",
std::env::var("UBSAN_OPTIONS").unwrap_or_default(),
)
.stdout(std::process::Stdio::piped())
.stderr(std::process::Stdio::piped())
.spawn()
.context("spawn postgres")?;
info!("spawned postgres, waiting for it to become ready");
tokio::spawn(
child_stdio_to_log::relay_process_output(
postgres_proc.stdout.take(),
postgres_proc.stderr.take(),
)
.instrument(info_span!("postgres")),
);
async fn wait_until_ready(connstring: String, create_dbname: String) {
// Create neondb database in the running postgres
let restore_pg_connstring =
format!("host=localhost port={pg_port} user={superuser} dbname=postgres");
let start_time = std::time::Instant::now();
loop {
@@ -276,12 +289,7 @@ async fn wait_until_ready(connstring: String, create_dbname: String) {
std::process::exit(1);
}
match tokio_postgres::connect(
&connstring.replace("dbname=neondb", "dbname=postgres"),
tokio_postgres::NoTls,
)
.await
{
match tokio_postgres::connect(&restore_pg_connstring, tokio_postgres::NoTls).await {
Ok((client, connection)) => {
// Spawn the connection handling task to maintain the connection
tokio::spawn(async move {
@@ -290,12 +298,9 @@ async fn wait_until_ready(connstring: String, create_dbname: String) {
}
});
match client
.simple_query(format!("CREATE DATABASE {create_dbname};").as_str())
.await
{
match client.simple_query("CREATE DATABASE neondb;").await {
Ok(_) => {
info!("created {} database", create_dbname);
info!("created neondb database");
break;
}
Err(e) => {
@@ -319,16 +324,10 @@ async fn wait_until_ready(connstring: String, create_dbname: String) {
}
}
}
}
async fn run_dump_restore(
workdir: Utf8PathBuf,
pg_bin_dir: Utf8PathBuf,
pg_lib_dir: Utf8PathBuf,
source_connstring: String,
destination_connstring: String,
) -> Result<(), anyhow::Error> {
let dumpdir = workdir.join("dumpdir");
let restore_pg_connstring = restore_pg_connstring.replace("dbname=postgres", "dbname=neondb");
let dumpdir = working_directory.join("dumpdir");
let common_args = [
// schema mapping (prob suffices to specify them on one side)
@@ -357,18 +356,10 @@ async fn run_dump_restore(
.arg("--no-sync")
// POSITIONAL args
// source db (db name included in connection string)
.arg(&source_connstring)
.arg(&source_connection_string)
// how we run it
.env_clear()
.env("LD_LIBRARY_PATH", &pg_lib_dir)
.env(
"ASAN_OPTIONS",
std::env::var("ASAN_OPTIONS").unwrap_or_default(),
)
.env(
"UBSAN_OPTIONS",
std::env::var("UBSAN_OPTIONS").unwrap_or_default(),
)
.kill_on_drop(true)
.stdout(std::process::Stdio::piped())
.stderr(std::process::Stdio::piped())
@@ -385,31 +376,24 @@ async fn run_dump_restore(
let st = pg_dump.wait().await.context("wait for pg_dump")?;
info!(status=?st, "pg_dump exited");
if !st.success() {
error!(status=%st, "pg_dump failed, restore will likely fail as well");
bail!("pg_dump failed");
warn!(status=%st, "pg_dump failed, restore will likely fail as well");
}
}
// TODO: maybe do it in a streaming way, plenty of internal research done on this already
// TODO: do it in a streaming way, plenty of internal research done on this already
// TODO: do the unlogged table trick
info!("restore from working directory into vanilla postgres");
{
let mut pg_restore = tokio::process::Command::new(pg_bin_dir.join("pg_restore"))
.args(&common_args)
.arg("-d")
.arg(&destination_connstring)
.arg(&restore_pg_connstring)
// POSITIONAL args
.arg(&dumpdir)
// how we run it
.env_clear()
.env("LD_LIBRARY_PATH", &pg_lib_dir)
.env(
"ASAN_OPTIONS",
std::env::var("ASAN_OPTIONS").unwrap_or_default(),
)
.env(
"UBSAN_OPTIONS",
std::env::var("UBSAN_OPTIONS").unwrap_or_default(),
)
.kill_on_drop(true)
.stdout(std::process::Stdio::piped())
.stderr(std::process::Stdio::piped())
@@ -427,261 +411,48 @@ async fn run_dump_restore(
let st = pg_restore.wait().await.context("wait for pg_restore")?;
info!(status=?st, "pg_restore exited");
if !st.success() {
error!(status=%st, "pg_restore failed, restore will likely fail as well");
bail!("pg_restore failed");
warn!(status=%st, "pg_restore failed, restore will likely fail as well");
}
}
Ok(())
}
#[allow(clippy::too_many_arguments)]
async fn cmd_pgdata(
s3_client: Option<aws_sdk_s3::Client>,
kms_client: Option<aws_sdk_kms::Client>,
maybe_s3_prefix: Option<s3_uri::S3Uri>,
maybe_spec: Option<Spec>,
source_connection_string: Option<String>,
interactive: bool,
pg_port: u16,
workdir: Utf8PathBuf,
pg_bin_dir: Utf8PathBuf,
pg_lib_dir: Utf8PathBuf,
num_cpus: Option<usize>,
memory_mb: Option<usize>,
) -> Result<(), anyhow::Error> {
if maybe_spec.is_none() && source_connection_string.is_none() {
bail!("spec must be provided for pgdata command");
}
if maybe_spec.is_some() && source_connection_string.is_some() {
bail!("only one of spec or source_connection_string can be provided");
}
let source_connection_string = if let Some(spec) = maybe_spec {
match spec.encryption_secret {
EncryptionSecret::KMS { key_id } => {
decode_connstring(
kms_client.as_ref().unwrap(),
&key_id,
spec.source_connstring_ciphertext_base64,
)
.await?
}
}
} else {
source_connection_string.unwrap()
};
let superuser = "cloud_admin";
let destination_connstring = format!(
"host=localhost port={} user={} dbname=neondb",
pg_port, superuser
);
let pgdata_dir = workdir.join("pgdata");
let mut proc = PostgresProcess::new(pgdata_dir.clone(), pg_bin_dir.clone(), pg_lib_dir.clone());
let nproc = num_cpus.unwrap_or_else(num_cpus::get);
let memory_mb = memory_mb.unwrap_or(256);
proc.start(superuser, pg_port, nproc, memory_mb).await?;
wait_until_ready(destination_connstring.clone(), "neondb".to_string()).await;
run_dump_restore(
workdir.clone(),
pg_bin_dir,
pg_lib_dir,
source_connection_string,
destination_connstring,
)
.await?;
// If interactive mode, wait for Ctrl+C
if interactive {
if args.interactive {
info!("Running in interactive mode. Press Ctrl+C to shut down.");
tokio::signal::ctrl_c().await.context("wait for ctrl-c")?;
}
proc.shutdown().await?;
info!("shutdown postgres");
{
nix::sys::signal::kill(
Pid::from_raw(
i32::try_from(postgres_proc.id().unwrap()).expect("convert child pid to i32"),
),
nix::sys::signal::SIGTERM,
)
.context("signal postgres to shut down")?;
postgres_proc
.wait()
.await
.context("wait for postgres to shut down")?;
}
// Only sync if s3_prefix was specified
if let Some(s3_prefix) = maybe_s3_prefix {
if let Some(s3_prefix) = args.s3_prefix {
info!("upload pgdata");
aws_s3_sync::upload_dir_recursive(
s3_client.as_ref().unwrap(),
Utf8Path::new(&pgdata_dir),
&s3_prefix.append("/pgdata/"),
)
.await
.context("sync dump directory to destination")?;
aws_s3_sync::sync(Utf8Path::new(&pgdata_dir), &s3_prefix.append("/pgdata/"))
.await
.context("sync dump directory to destination")?;
info!("write status");
{
let status_dir = workdir.join("status");
let status_dir = working_directory.join("status");
std::fs::create_dir(&status_dir).context("create status directory")?;
let status_file = status_dir.join("pgdata");
std::fs::write(&status_file, serde_json::json!({"done": true}).to_string())
.context("write status file")?;
aws_s3_sync::upload_dir_recursive(
s3_client.as_ref().unwrap(),
&status_dir,
&s3_prefix.append("/status/"),
)
.await
.context("sync status directory to destination")?;
}
}
Ok(())
}
async fn cmd_dumprestore(
kms_client: Option<aws_sdk_kms::Client>,
maybe_spec: Option<Spec>,
source_connection_string: Option<String>,
destination_connection_string: Option<String>,
workdir: Utf8PathBuf,
pg_bin_dir: Utf8PathBuf,
pg_lib_dir: Utf8PathBuf,
) -> Result<(), anyhow::Error> {
let (source_connstring, destination_connstring) = if let Some(spec) = maybe_spec {
match spec.encryption_secret {
EncryptionSecret::KMS { key_id } => {
let source = decode_connstring(
kms_client.as_ref().unwrap(),
&key_id,
spec.source_connstring_ciphertext_base64,
)
.await?;
let dest = if let Some(dest_ciphertext) =
spec.destination_connstring_ciphertext_base64
{
decode_connstring(kms_client.as_ref().unwrap(), &key_id, dest_ciphertext)
.await?
} else {
bail!(
"destination connection string must be provided in spec for dump_restore command"
);
};
(source, dest)
}
}
} else {
(
source_connection_string.unwrap(),
if let Some(val) = destination_connection_string {
val
} else {
bail!("destination connection string must be provided for dump_restore command");
},
)
};
run_dump_restore(
workdir,
pg_bin_dir,
pg_lib_dir,
source_connstring,
destination_connstring,
)
.await
}
#[tokio::main]
pub(crate) async fn main() -> anyhow::Result<()> {
utils::logging::init(
utils::logging::LogFormat::Json,
utils::logging::TracingErrorLayerEnablement::EnableWithRustLogFilter,
utils::logging::Output::Stdout,
)?;
info!("starting");
let args = Args::parse();
// Initialize AWS clients only if s3_prefix is specified
let (s3_client, kms_client) = if args.s3_prefix.is_some() {
let config = aws_config::load_defaults(BehaviorVersion::v2024_03_28()).await;
let s3_client = aws_sdk_s3::Client::new(&config);
let kms = aws_sdk_kms::Client::new(&config);
(Some(s3_client), Some(kms))
} else {
(None, None)
};
let spec: Option<Spec> = if let Some(s3_prefix) = &args.s3_prefix {
let spec_key = s3_prefix.append("/spec.json");
let object = s3_client
.as_ref()
.unwrap()
.get_object()
.bucket(&spec_key.bucket)
.key(spec_key.key)
.send()
.await
.context("get spec from s3")?
.body
.collect()
.await
.context("download spec body")?;
serde_json::from_slice(&object.into_bytes()).context("parse spec as json")?
} else {
None
};
match tokio::fs::create_dir(&args.working_directory).await {
Ok(()) => {}
Err(e) if e.kind() == std::io::ErrorKind::AlreadyExists => {
if !is_directory_empty(&args.working_directory)
aws_s3_sync::sync(&status_dir, &s3_prefix.append("/status/"))
.await
.context("check if working directory is empty")?
{
bail!("working directory is not empty");
} else {
// ok
}
}
Err(e) => return Err(anyhow::Error::new(e).context("create working directory")),
}
match args.command {
Command::Pgdata {
source_connection_string,
interactive,
pg_port,
num_cpus,
memory_mb,
} => {
cmd_pgdata(
s3_client,
kms_client,
args.s3_prefix,
spec,
source_connection_string,
interactive,
pg_port,
args.working_directory,
args.pg_bin_dir,
args.pg_lib_dir,
num_cpus,
memory_mb,
)
.await?;
}
Command::DumpRestore {
source_connection_string,
destination_connection_string,
} => {
cmd_dumprestore(
kms_client,
spec,
source_connection_string,
destination_connection_string,
args.working_directory,
args.pg_bin_dir,
args.pg_lib_dir,
)
.await?;
.context("sync status directory to destination")?;
}
}

View File

@@ -1,101 +1,24 @@
use camino::{Utf8Path, Utf8PathBuf};
use tokio::task::JoinSet;
use tracing::{info, warn};
use walkdir::WalkDir;
use anyhow::Context;
use camino::Utf8Path;
use super::s3_uri::S3Uri;
const MAX_PARALLEL_UPLOADS: usize = 10;
/// Upload all files from 'local' to 'remote'
pub(crate) async fn upload_dir_recursive(
s3_client: &aws_sdk_s3::Client,
local: &Utf8Path,
remote: &S3Uri,
) -> anyhow::Result<()> {
// Recursively scan directory
let mut dirwalker = WalkDir::new(local)
.into_iter()
.map(|entry| {
let entry = entry?;
let file_type = entry.file_type();
let path = <&Utf8Path>::try_from(entry.path())?.to_path_buf();
Ok((file_type, path))
})
.filter_map(|e: anyhow::Result<(std::fs::FileType, Utf8PathBuf)>| {
match e {
Ok((file_type, path)) if file_type.is_file() => Some(Ok(path)),
Ok((file_type, _path)) if file_type.is_dir() => {
// The WalkDir iterator will recurse into directories, but we don't want
// to do anything with directories as such. There's no concept of uploading
// an empty directory to S3.
None
}
Ok((file_type, path)) if file_type.is_symlink() => {
// huh, didn't expect a symlink. Can't upload that to S3. Warn and skip.
warn!("cannot upload symlink ({})", path);
None
}
Ok((_file_type, path)) => {
// should not happen
warn!("directory entry has unexpected type ({})", path);
None
}
Err(e) => Some(Err(e)),
}
});
// Spawn upload tasks for each file, keeping MAX_PARALLEL_UPLOADS active in
// parallel.
let mut joinset = JoinSet::new();
loop {
// Could we upload more?
while joinset.len() < MAX_PARALLEL_UPLOADS {
if let Some(full_local_path) = dirwalker.next() {
let full_local_path = full_local_path?;
let relative_local_path = full_local_path
.strip_prefix(local)
.expect("all paths start from the walkdir root");
let remote_path = remote.append(relative_local_path.as_str());
info!(
"starting upload of {} to {}",
&full_local_path, &remote_path
);
let upload_task = upload_file(s3_client.clone(), full_local_path, remote_path);
joinset.spawn(upload_task);
} else {
info!("draining upload tasks");
break;
}
}
// Wait for an upload to complete
if let Some(res) = joinset.join_next().await {
let _ = res?;
} else {
// all done!
break;
}
pub(crate) async fn sync(local: &Utf8Path, remote: &S3Uri) -> anyhow::Result<()> {
let mut builder = tokio::process::Command::new("aws");
builder
.arg("s3")
.arg("sync")
.arg(local.as_str())
.arg(remote.to_string());
let st = builder
.spawn()
.context("spawn aws s3 sync")?
.wait()
.await
.context("wait for aws s3 sync")?;
if st.success() {
Ok(())
} else {
Err(anyhow::anyhow!("aws s3 sync failed"))
}
Ok(())
}
pub(crate) async fn upload_file(
s3_client: aws_sdk_s3::Client,
local_path: Utf8PathBuf,
remote: S3Uri,
) -> anyhow::Result<()> {
use aws_smithy_types::byte_stream::ByteStream;
let stream = ByteStream::from_path(&local_path).await?;
let _result = s3_client
.put_object()
.bucket(remote.bucket)
.key(&remote.key)
.body(stream)
.send()
.await?;
info!("upload of {} to {} finished", &local_path, &remote.key);
Ok(())
}

View File

@@ -1,6 +1,5 @@
use std::str::FromStr;
use anyhow::Result;
use std::str::FromStr;
/// Struct to hold parsed S3 components
#[derive(Debug, Clone, PartialEq, Eq)]

View File

@@ -1,20 +1,18 @@
use std::path::Path;
use std::process::Stdio;
use std::result::Result;
use std::sync::Arc;
use compute_api::responses::CatalogObjects;
use futures::Stream;
use postgres::NoTls;
use tokio::io::{AsyncBufReadExt, BufReader};
use tokio::process::Command;
use tokio::spawn;
use std::{path::Path, process::Stdio, result::Result, sync::Arc};
use tokio::{
io::{AsyncBufReadExt, BufReader},
process::Command,
spawn,
};
use tokio_stream::{self as stream, StreamExt};
use tokio_util::codec::{BytesCodec, FramedRead};
use tracing::warn;
use crate::compute::ComputeNode;
use crate::pg_helpers::{get_existing_dbs_async, get_existing_roles_async, postgres_conf_for_db};
use compute_api::responses::CatalogObjects;
pub async fn get_dbs_and_roles(compute: &Arc<ComputeNode>) -> anyhow::Result<CatalogObjects> {
let conf = compute.get_tokio_conn_conf(Some("compute_ctl:get_dbs_and_roles"));
@@ -57,7 +55,7 @@ pub enum SchemaDumpError {
pub async fn get_database_schema(
compute: &Arc<ComputeNode>,
dbname: &str,
) -> Result<impl Stream<Item = Result<bytes::Bytes, std::io::Error>> + use<>, SchemaDumpError> {
) -> Result<impl Stream<Item = Result<bytes::Bytes, std::io::Error>>, SchemaDumpError> {
let pgbin = &compute.pgbin;
let basepath = Path::new(pgbin).parent().unwrap();
let pgdump = basepath.join("pg_dump");

View File

@@ -1,4 +1,4 @@
use anyhow::{Ok, Result, anyhow};
use anyhow::{anyhow, Ok, Result};
use tokio_postgres::NoTls;
use tracing::{error, instrument, warn};

View File

@@ -1,38 +1,42 @@
use std::collections::{HashMap, HashSet};
use std::env;
use std::fs;
use std::iter::once;
use std::os::unix::fs::{PermissionsExt, symlink};
use std::os::unix::fs::{symlink, PermissionsExt};
use std::path::Path;
use std::process::{Command, Stdio};
use std::str::FromStr;
use std::sync::atomic::{AtomicU32, Ordering};
use std::sync::atomic::AtomicU32;
use std::sync::atomic::Ordering;
use std::sync::{Arc, Condvar, Mutex, RwLock};
use std::time::{Duration, Instant};
use std::{env, fs};
use std::time::Duration;
use std::time::Instant;
use anyhow::{Context, Result};
use chrono::{DateTime, Utc};
use compute_api::privilege::Privilege;
use compute_api::responses::{ComputeMetrics, ComputeStatus};
use compute_api::spec::{
ComputeFeature, ComputeMode, ComputeSpec, Database, ExtVersion, PgIdent, Role,
};
use futures::StreamExt;
use compute_api::spec::{Database, PgIdent, Role};
use futures::future::join_all;
use futures::stream::FuturesUnordered;
use nix::sys::signal::{Signal, kill};
use futures::StreamExt;
use nix::unistd::Pid;
use postgres;
use postgres::NoTls;
use postgres::error::SqlState;
use remote_storage::{DownloadError, RemotePath};
use tokio::spawn;
use postgres::NoTls;
use tracing::{debug, error, info, instrument, warn};
use utils::id::{TenantId, TimelineId};
use utils::lsn::Lsn;
use compute_api::privilege::Privilege;
use compute_api::responses::{ComputeMetrics, ComputeStatus};
use compute_api::spec::{ComputeFeature, ComputeMode, ComputeSpec, ExtVersion};
use utils::measured_stream::MeasuredReader;
use crate::disk_quota::set_disk_quota;
use nix::sys::signal::{kill, Signal};
use remote_storage::{DownloadError, RemotePath};
use tokio::spawn;
use crate::installed_extensions::get_installed_extensions;
use crate::local_proxy;
use crate::pg_helpers::*;
use crate::spec::*;
use crate::spec_apply::ApplySpecPhase::{
@@ -41,13 +45,14 @@ use crate::spec_apply::ApplySpecPhase::{
HandleNeonExtension, HandleOtherExtensions, RenameAndDeleteDatabases, RenameRoles,
RunInEachDatabase,
};
use crate::spec_apply::PerDatabasePhase;
use crate::spec_apply::PerDatabasePhase::{
ChangeSchemaPerms, DeleteDBRoleReferences, DropLogicalSubscriptions, HandleAnonExtension,
};
use crate::spec_apply::{DB, MutableApplyContext, PerDatabasePhase, apply_operations};
use crate::swap::resize_swap;
use crate::spec_apply::{apply_operations, MutableApplyContext, DB};
use crate::sync_sk::{check_if_synced, ping_safekeeper};
use crate::{config, extension_server, local_proxy};
use crate::{config, extension_server};
pub static SYNC_SAFEKEEPERS_PID: AtomicU32 = AtomicU32::new(0);
pub static PG_PID: AtomicU32 = AtomicU32::new(0);
@@ -93,10 +98,6 @@ pub struct ComputeNode {
// key: ext_archive_name, value: started download time, download_completed?
pub ext_download_progress: RwLock<HashMap<String, (DateTime<Utc>, bool)>>,
pub build_tag: String,
/// Initialized from cli.resize_swap_on_bind
pub resize_swap_on_bind: bool,
/// Initialized from cli.set_disk_quota_for_fs
pub set_disk_quota_for_fs: Option<String>,
}
// store some metrics about download size that might impact startup time
@@ -545,7 +546,6 @@ impl ComputeNode {
// Fast path for sync_safekeepers. If they're already synced we get the lsn
// in one roundtrip. If not, we should do a full sync_safekeepers.
#[instrument(skip_all)]
pub fn check_safekeepers_synced(&self, compute_state: &ComputeState) -> Result<Option<Lsn>> {
let start_time = Utc::now();
@@ -1317,7 +1317,7 @@ impl ComputeNode {
// Merge-apply spec & changes to PostgreSQL state.
self.apply_spec_sql(spec.clone(), conf.clone(), max_concurrent_connections)?;
if let Some(local_proxy) = &spec.clone().local_proxy_config {
if let Some(ref local_proxy) = &spec.clone().local_proxy_config {
info!("configuring local_proxy");
local_proxy::configure(local_proxy).context("apply_config local_proxy")?;
}
@@ -1434,59 +1434,12 @@ impl ComputeNode {
Ok(())
}
/// Configure some VM parameters like swap and disk quota
#[instrument(skip_all)]
pub fn configure_vm(&self, spec: &ComputeSpec) -> Result<()> {
// Resize swap to the desired size if the compute spec says so
if let (Some(size_bytes), true) = (spec.swap_size_bytes, self.resize_swap_on_bind) {
// To avoid 'swapoff' hitting postgres startup, we need to run resize-swap to completion
// *before* starting postgres.
//
// In theory, we could do this asynchronously if SkipSwapon was enabled for VMs, but this
// carries a risk of introducing hard-to-debug issues - e.g. if postgres sometimes gets
// OOM-killed during startup because swap wasn't available yet.
match resize_swap(size_bytes) {
Ok(()) => {
let size_mib = size_bytes as f32 / (1 << 20) as f32; // just for more coherent display.
info!(%size_bytes, %size_mib, "resized swap");
}
Err(err) => {
let err = err.context("failed to resize swap");
error!("{err:#}");
return Err(err);
}
}
}
// Set disk quota if the compute spec says so
if let (Some(disk_quota_bytes), Some(disk_quota_fs_mountpoint)) =
(spec.disk_quota_bytes, self.set_disk_quota_for_fs.as_ref())
{
match set_disk_quota(disk_quota_bytes, disk_quota_fs_mountpoint) {
Ok(()) => {
let size_mib = disk_quota_bytes as f32 / (1 << 20) as f32; // just for more coherent display.
info!(%disk_quota_bytes, %size_mib, "set disk quota");
}
Err(err) => {
let err = err.context("failed to set disk quota");
error!("{err:#}");
return Err(err);
}
}
}
Ok(())
}
#[instrument(skip_all)]
pub fn start_compute(
&self,
) -> Result<(std::process::Child, tokio::task::JoinHandle<Result<()>>)> {
let compute_state = self.state.lock().unwrap().clone();
let pspec = compute_state.pspec.as_ref().expect("spec must be set");
info!(
"starting compute for project {}, operation {}, tenant {}, timeline {}",
pspec.spec.cluster.cluster_id.as_deref().unwrap_or("None"),
@@ -1495,11 +1448,9 @@ impl ComputeNode {
pspec.timeline_id,
);
self.configure_vm(&pspec.spec)?;
// Configure pgbouncer
// tune pgbouncer
if let Some(pgbouncer_settings) = &pspec.spec.pgbouncer_settings {
info!("configuring pgbouncer");
info!("tuning pgbouncer");
// Spawn a background task to do the tuning,
// so that we don't block the main thread that starts Postgres.
@@ -1525,11 +1476,14 @@ impl ComputeNode {
});
}
info!(
"start_compute spec.remote_extensions {:?}",
pspec.spec.remote_extensions
);
// This part is sync, because we need to download
// remote shared_preload_libraries before postgres start (if any)
if let Some(remote_extensions) = &pspec.spec.remote_extensions {
info!(?remote_extensions, "processing remote extensions");
// First, create control files for all availale extensions
extension_server::create_control_files(remote_extensions, &self.pgbin);
@@ -1548,7 +1502,7 @@ impl ComputeNode {
state.metrics.largest_ext_size = remote_ext_metrics.largest_ext_size;
state.metrics.total_ext_download_size = remote_ext_metrics.total_ext_download_size;
info!(
"loading shared_preload_libraries from remote extensions took {:?}ms",
"Loading shared_preload_libraries took {:?}ms",
library_load_time
);
info!("{:?}", remote_ext_metrics);
@@ -1583,9 +1537,7 @@ impl ComputeNode {
&postgresql_conf_path,
"neon.disable_logical_replication_subscribers=false",
)? {
info!(
"updated postgresql.conf to set neon.disable_logical_replication_subscribers=false"
);
info!("updated postgresql.conf to set neon.disable_logical_replication_subscribers=false");
}
self.pg_reload_conf()?;
}
@@ -1607,7 +1559,6 @@ impl ComputeNode {
});
}
let metrics: ComputeMetrics;
let startup_end_time = Utc::now();
{
let mut state = self.state.lock().unwrap();
@@ -1626,17 +1577,21 @@ impl ComputeNode {
.to_std()
.unwrap()
.as_millis() as u64;
metrics = state.metrics.clone();
}
self.set_status(ComputeStatus::Running);
// Log metrics so that we can search for slow operations in logs
info!(
?metrics,
"finished configuration of compute for project {}",
pspec.spec.cluster.cluster_id.as_deref().unwrap_or("None")
);
// Log metrics so that we can search for slow operations in logs
let metrics = {
let state = self.state.lock().unwrap();
state.metrics.clone()
};
info!(?metrics, "compute start finished");
Ok(pg_process)
}
@@ -1809,9 +1764,7 @@ LIMIT 100",
info!("extension already downloaded, skipping re-download");
return Ok(0);
} else if start_time_delta < HANG_TIMEOUT && !first_try {
info!(
"download {ext_archive_name} already started by another process, hanging untill completion or timeout"
);
info!("download {ext_archive_name} already started by another process, hanging untill completion or timeout");
let mut interval = tokio::time::interval(tokio::time::Duration::from_millis(500));
loop {
info!("waiting for download");

View File

@@ -4,9 +4,10 @@ use std::io::prelude::*;
use std::path::Path;
use anyhow::Result;
use compute_api::spec::{ComputeMode, ComputeSpec, GenericOption};
use crate::pg_helpers::{GenericOptionExt, PgOptionsSerialize, escape_conf_value};
use crate::pg_helpers::escape_conf_value;
use crate::pg_helpers::{GenericOptionExt, PgOptionsSerialize};
use compute_api::spec::{ComputeMode, ComputeSpec, GenericOption};
/// Check that `line` is inside a text file and put it there if it is not.
/// Create file if it doesn't exist.

View File

@@ -1,9 +1,10 @@
use std::sync::Arc;
use std::thread;
use compute_api::responses::ComputeStatus;
use tracing::{error, info, instrument};
use compute_api::responses::ComputeStatus;
use crate::compute::ComputeNode;
#[instrument(skip_all)]

View File

@@ -1,11 +1,9 @@
use anyhow::Context;
use tracing::instrument;
pub const DISK_QUOTA_BIN: &str = "/neonvm/bin/set-disk-quota";
/// If size_bytes is 0, it disables the quota. Otherwise, it sets filesystem quota to size_bytes.
/// `fs_mountpoint` should point to the mountpoint of the filesystem where the quota should be set.
#[instrument]
pub fn set_disk_quota(size_bytes: u64, fs_mountpoint: &str) -> anyhow::Result<()> {
let size_kb = size_bytes / 1024;
// run `/neonvm/bin/set-disk-quota {size_kb} {mountpoint}`

View File

@@ -71,15 +71,15 @@ More specifically, here is an example ext_index.json
}
}
*/
use std::path::Path;
use std::str;
use anyhow::{Context, Result, bail};
use anyhow::Result;
use anyhow::{bail, Context};
use bytes::Bytes;
use compute_api::spec::RemoteExtSpec;
use regex::Regex;
use remote_storage::*;
use reqwest::StatusCode;
use std::path::Path;
use std::str;
use tar::Archive;
use tracing::info;
use tracing::log::warn;
@@ -244,10 +244,7 @@ pub fn create_control_files(remote_extensions: &RemoteExtSpec, pgbin: &str) {
info!("writing file {:?}{:?}", control_path, control_content);
std::fs::write(control_path, control_content).unwrap();
} else {
warn!(
"control file {:?} exists both locally and remotely. ignoring the remote version.",
control_path
);
warn!("control file {:?} exists both locally and remotely. ignoring the remote version.", control_path);
}
}
}

View File

@@ -1,7 +1,6 @@
use std::ops::{Deref, DerefMut};
use axum::extract::rejection::JsonRejection;
use axum::extract::{FromRequest, Request};
use axum::extract::{rejection::JsonRejection, FromRequest, Request};
use compute_api::responses::GenericAPIError;
use http::StatusCode;

View File

@@ -1,10 +1,8 @@
use std::ops::{Deref, DerefMut};
use axum::extract::FromRequestParts;
use axum::extract::rejection::PathRejection;
use axum::extract::{rejection::PathRejection, FromRequestParts};
use compute_api::responses::GenericAPIError;
use http::StatusCode;
use http::request::Parts;
use http::{request::Parts, StatusCode};
/// Custom `Path` extractor, so that we can format errors into
/// `JsonResponse<GenericAPIError>`.

View File

@@ -1,10 +1,8 @@
use std::ops::{Deref, DerefMut};
use axum::extract::FromRequestParts;
use axum::extract::rejection::QueryRejection;
use axum::extract::{rejection::QueryRejection, FromRequestParts};
use compute_api::responses::GenericAPIError;
use http::StatusCode;
use http::request::Parts;
use http::{request::Parts, StatusCode};
/// Custom `Query` extractor, so that we can format errors into
/// `JsonResponse<GenericAPIError>`.

View File

@@ -1,8 +1,6 @@
use axum::body::Body;
use axum::response::Response;
use axum::{body::Body, response::Response};
use compute_api::responses::{ComputeStatus, GenericAPIError};
use http::StatusCode;
use http::header::CONTENT_TYPE;
use http::{header::CONTENT_TYPE, StatusCode};
use serde::Serialize;
use tracing::error;

View File

@@ -1,13 +1,10 @@
use std::sync::Arc;
use axum::extract::State;
use axum::response::Response;
use axum::{extract::State, response::Response};
use compute_api::responses::ComputeStatus;
use http::StatusCode;
use crate::checker::check_writability;
use crate::compute::ComputeNode;
use crate::http::JsonResponse;
use crate::{checker::check_writability, compute::ComputeNode, http::JsonResponse};
/// Check that the compute is currently running.
pub(in crate::http) async fn is_writable(State(compute): State<Arc<ComputeNode>>) -> Response {

View File

@@ -1,16 +1,18 @@
use std::sync::Arc;
use axum::extract::State;
use axum::response::Response;
use compute_api::requests::ConfigurationRequest;
use compute_api::responses::{ComputeStatus, ComputeStatusResponse};
use axum::{extract::State, response::Response};
use compute_api::{
requests::ConfigurationRequest,
responses::{ComputeStatus, ComputeStatusResponse},
};
use http::StatusCode;
use tokio::task;
use tracing::info;
use crate::compute::{ComputeNode, ParsedSpec};
use crate::http::JsonResponse;
use crate::http::extract::Json;
use crate::{
compute::{ComputeNode, ParsedSpec},
http::{extract::Json, JsonResponse},
};
// Accept spec in JSON format and request compute configuration. If anything
// goes wrong after we set the compute status to `ConfigurationPending` and

View File

@@ -1,16 +1,14 @@
use std::sync::Arc;
use axum::body::Body;
use axum::extract::State;
use axum::response::Response;
use http::StatusCode;
use http::header::CONTENT_TYPE;
use axum::{body::Body, extract::State, response::Response};
use http::{header::CONTENT_TYPE, StatusCode};
use serde::Deserialize;
use crate::catalog::{SchemaDumpError, get_database_schema};
use crate::compute::ComputeNode;
use crate::http::JsonResponse;
use crate::http::extract::Query;
use crate::{
catalog::{get_database_schema, SchemaDumpError},
compute::ComputeNode,
http::{extract::Query, JsonResponse},
};
#[derive(Debug, Clone, Deserialize)]
pub(in crate::http) struct DatabaseSchemaParams {

View File

@@ -1,12 +1,9 @@
use std::sync::Arc;
use axum::extract::State;
use axum::response::Response;
use axum::{extract::State, response::Response};
use http::StatusCode;
use crate::catalog::get_dbs_and_roles;
use crate::compute::ComputeNode;
use crate::http::JsonResponse;
use crate::{catalog::get_dbs_and_roles, compute::ComputeNode, http::JsonResponse};
/// Get the databases and roles from the compute.
pub(in crate::http) async fn get_catalog_objects(

View File

@@ -1,13 +1,19 @@
use std::sync::Arc;
use axum::extract::State;
use axum::response::{IntoResponse, Response};
use axum::{
extract::State,
response::{IntoResponse, Response},
};
use http::StatusCode;
use serde::Deserialize;
use crate::compute::ComputeNode;
use crate::http::JsonResponse;
use crate::http::extract::{Path, Query};
use crate::{
compute::ComputeNode,
http::{
extract::{Path, Query},
JsonResponse,
},
};
#[derive(Debug, Clone, Deserialize)]
pub(in crate::http) struct ExtensionServerParams {

View File

@@ -1,14 +1,16 @@
use std::sync::Arc;
use axum::extract::State;
use axum::response::Response;
use compute_api::requests::ExtensionInstallRequest;
use compute_api::responses::{ComputeStatus, ExtensionInstallResponse};
use axum::{extract::State, response::Response};
use compute_api::{
requests::ExtensionInstallRequest,
responses::{ComputeStatus, ExtensionInstallResponse},
};
use http::StatusCode;
use crate::compute::ComputeNode;
use crate::http::JsonResponse;
use crate::http::extract::Json;
use crate::{
compute::ComputeNode,
http::{extract::Json, JsonResponse},
};
/// Install a extension.
pub(in crate::http) async fn install_extension(

View File

@@ -17,8 +17,7 @@ pub struct FailpointConfig {
pub actions: String,
}
use crate::http::JsonResponse;
use crate::http::extract::Json;
use crate::http::{extract::Json, JsonResponse};
/// Configure failpoints for testing purposes.
pub(in crate::http) async fn configure_failpoints(

View File

@@ -1,14 +1,16 @@
use std::sync::Arc;
use axum::extract::State;
use axum::response::Response;
use compute_api::requests::SetRoleGrantsRequest;
use compute_api::responses::{ComputeStatus, SetRoleGrantsResponse};
use axum::{extract::State, response::Response};
use compute_api::{
requests::SetRoleGrantsRequest,
responses::{ComputeStatus, SetRoleGrantsResponse},
};
use http::StatusCode;
use crate::compute::ComputeNode;
use crate::http::JsonResponse;
use crate::http::extract::Json;
use crate::{
compute::ComputeNode,
http::{extract::Json, JsonResponse},
};
/// Add grants for a role.
pub(in crate::http) async fn add_grant(

View File

@@ -1,12 +1,10 @@
use std::sync::Arc;
use axum::extract::State;
use axum::response::Response;
use axum::{extract::State, response::Response};
use compute_api::responses::ComputeStatus;
use http::StatusCode;
use crate::compute::ComputeNode;
use crate::http::JsonResponse;
use crate::{compute::ComputeNode, http::JsonResponse};
/// Collect current Postgres usage insights.
pub(in crate::http) async fn get_insights(State(compute): State<Arc<ComputeNode>>) -> Response {

View File

@@ -1,12 +1,10 @@
use axum::body::Body;
use axum::response::Response;
use http::StatusCode;
use axum::{body::Body, response::Response};
use http::header::CONTENT_TYPE;
use http::StatusCode;
use metrics::proto::MetricFamily;
use metrics::{Encoder, TextEncoder};
use crate::http::JsonResponse;
use crate::metrics::collect;
use crate::{http::JsonResponse, metrics::collect};
/// Expose Prometheus metrics.
pub(in crate::http) async fn get_metrics() -> Response {

View File

@@ -1,11 +1,9 @@
use std::sync::Arc;
use axum::extract::State;
use axum::response::Response;
use axum::{extract::State, response::Response};
use http::StatusCode;
use crate::compute::ComputeNode;
use crate::http::JsonResponse;
use crate::{compute::ComputeNode, http::JsonResponse};
/// Get startup metrics.
pub(in crate::http) async fn get_metrics(State(compute): State<Arc<ComputeNode>>) -> Response {

View File

@@ -1,13 +1,9 @@
use std::ops::Deref;
use std::sync::Arc;
use std::{ops::Deref, sync::Arc};
use axum::extract::State;
use axum::http::StatusCode;
use axum::response::Response;
use axum::{extract::State, http::StatusCode, response::Response};
use compute_api::responses::ComputeStatusResponse;
use crate::compute::ComputeNode;
use crate::http::JsonResponse;
use crate::{compute::ComputeNode, http::JsonResponse};
/// Retrieve the state of the comute.
pub(in crate::http) async fn get_status(State(compute): State<Arc<ComputeNode>>) -> Response {

View File

@@ -1,14 +1,18 @@
use std::sync::Arc;
use axum::extract::State;
use axum::response::{IntoResponse, Response};
use axum::{
extract::State,
response::{IntoResponse, Response},
};
use compute_api::responses::ComputeStatus;
use http::StatusCode;
use tokio::task;
use tracing::info;
use crate::compute::{ComputeNode, forward_termination_signal};
use crate::http::JsonResponse;
use crate::{
compute::{forward_termination_signal, ComputeNode},
http::JsonResponse,
};
/// Terminate the compute.
pub(in crate::http) async fn terminate(State(compute): State<Arc<ComputeNode>>) -> Response {

View File

@@ -1,20 +1,23 @@
use std::fmt::Display;
use std::net::{IpAddr, Ipv6Addr, SocketAddr};
use std::sync::Arc;
use std::time::Duration;
use std::{
fmt::Display,
net::{IpAddr, Ipv6Addr, SocketAddr},
sync::Arc,
time::Duration,
};
use anyhow::Result;
use axum::Router;
use axum::extract::Request;
use axum::middleware::{self, Next};
use axum::response::{IntoResponse, Response};
use axum::routing::{get, post};
use axum::{
extract::Request,
middleware::{self, Next},
response::{IntoResponse, Response},
routing::{get, post},
Router,
};
use http::StatusCode;
use tokio::net::TcpListener;
use tower::ServiceBuilder;
use tower_http::request_id::PropagateRequestIdLayer;
use tower_http::trace::TraceLayer;
use tracing::{Span, debug, error, info};
use tower_http::{request_id::PropagateRequestIdLayer, trace::TraceLayer};
use tracing::{debug, error, info, Span};
use uuid::Uuid;
use super::routes::{

View File

@@ -1,7 +1,7 @@
use compute_api::responses::{InstalledExtension, InstalledExtensions};
use std::collections::HashMap;
use anyhow::Result;
use compute_api::responses::{InstalledExtension, InstalledExtensions};
use postgres::{Client, NoTls};
use crate::metrics::INSTALLED_EXTENSIONS;

View File

@@ -1,15 +1,17 @@
use std::str::FromStr;
use std::sync::Arc;
use std::thread;
use std::time::{Duration, SystemTime};
use anyhow::{Result, bail};
use compute_api::spec::ComputeMode;
use anyhow::bail;
use anyhow::Result;
use postgres::{NoTls, SimpleQueryMessage};
use std::time::SystemTime;
use std::{str::FromStr, sync::Arc, thread, time::Duration};
use utils::id::TenantId;
use utils::id::TimelineId;
use compute_api::spec::ComputeMode;
use tracing::{info, warn};
use utils::id::{TenantId, TimelineId};
use utils::lsn::Lsn;
use utils::shard::{ShardCount, ShardNumber, TenantShardId};
use utils::{
lsn::Lsn,
shard::{ShardCount, ShardNumber, TenantShardId},
};
use crate::compute::ComputeNode;

View File

@@ -1,6 +1,6 @@
use metrics::core::Collector;
use metrics::proto::MetricFamily;
use metrics::{IntCounterVec, UIntGaugeVec, register_int_counter_vec, register_uint_gauge_vec};
use metrics::{register_int_counter_vec, register_uint_gauge_vec, IntCounterVec, UIntGaugeVec};
use once_cell::sync::Lazy;
pub(crate) static INSTALLED_EXTENSIONS: Lazy<UIntGaugeVec> = Lazy::new(|| {

View File

@@ -1,14 +1,13 @@
use std::sync::Arc;
use std::thread;
use std::time::Duration;
use std::{thread, time::Duration};
use chrono::{DateTime, Utc};
use compute_api::responses::ComputeStatus;
use compute_api::spec::ComputeFeature;
use postgres::{Client, NoTls};
use tracing::{debug, error, info, warn};
use crate::compute::ComputeNode;
use compute_api::responses::ComputeStatus;
use compute_api::spec::ComputeFeature;
const MONITOR_CHECK_INTERVAL: Duration = Duration::from_millis(500);

View File

@@ -9,8 +9,7 @@ use std::process::Child;
use std::str::FromStr;
use std::time::{Duration, Instant};
use anyhow::{Result, bail};
use compute_api::spec::{Database, GenericOption, GenericOptions, PgIdent, Role};
use anyhow::{bail, Result};
use futures::StreamExt;
use ini::Ini;
use notify::{RecursiveMode, Watcher};
@@ -22,6 +21,8 @@ use tokio_postgres;
use tokio_postgres::NoTls;
use tracing::{debug, error, info, instrument};
use compute_api::spec::{Database, GenericOption, GenericOptions, PgIdent, Role};
const POSTGRES_WAIT_TIMEOUT: Duration = Duration::from_millis(60 * 1000); // milliseconds
/// Escape a string for including it in a SQL literal.

View File

@@ -1,21 +1,19 @@
use anyhow::{anyhow, bail, Result};
use reqwest::StatusCode;
use std::fs::File;
use std::path::Path;
use anyhow::{Result, anyhow, bail};
use compute_api::responses::{
ComputeCtlConfig, ControlPlaneComputeStatus, ControlPlaneSpecResponse,
};
use compute_api::spec::ComputeSpec;
use reqwest::StatusCode;
use tokio_postgres::Client;
use tracing::{error, info, instrument, warn};
use crate::config;
use crate::metrics::{CPLANE_REQUESTS_TOTAL, CPlaneRequestRPC, UNKNOWN_HTTP_STATUS};
use crate::metrics::{CPlaneRequestRPC, CPLANE_REQUESTS_TOTAL, UNKNOWN_HTTP_STATUS};
use crate::migration::MigrationRunner;
use crate::params::PG_HBA_ALL_MD5;
use crate::pg_helpers::*;
use compute_api::responses::{ControlPlaneComputeStatus, ControlPlaneSpecResponse};
use compute_api::spec::ComputeSpec;
// Do control plane request and return response if any. In case of error it
// returns a bool flag indicating whether it makes sense to retry the request
// and a string with error message.
@@ -75,13 +73,14 @@ fn do_control_plane_request(
pub fn get_spec_from_control_plane(
base_uri: &str,
compute_id: &str,
) -> Result<(Option<ComputeSpec>, ComputeCtlConfig)> {
) -> Result<Option<ComputeSpec>> {
let cp_uri = format!("{base_uri}/compute/api/v2/computes/{compute_id}/spec");
let jwt: String = match std::env::var("NEON_CONTROL_PLANE_TOKEN") {
Ok(v) => v,
Err(_) => "".to_string(),
};
let mut attempt = 1;
let mut spec: Result<Option<ComputeSpec>> = Ok(None);
info!("getting spec from control plane: {}", cp_uri);
@@ -91,7 +90,7 @@ pub fn get_spec_from_control_plane(
// - no spec for compute yet (Empty state) -> return Ok(None)
// - got spec -> return Ok(Some(spec))
while attempt < 4 {
let result = match do_control_plane_request(&cp_uri, &jwt) {
spec = match do_control_plane_request(&cp_uri, &jwt) {
Ok(spec_resp) => {
CPLANE_REQUESTS_TOTAL
.with_label_values(&[
@@ -100,10 +99,10 @@ pub fn get_spec_from_control_plane(
])
.inc();
match spec_resp.status {
ControlPlaneComputeStatus::Empty => Ok((None, spec_resp.compute_ctl_config)),
ControlPlaneComputeStatus::Empty => Ok(None),
ControlPlaneComputeStatus::Attached => {
if let Some(spec) = spec_resp.spec {
Ok((Some(spec), spec_resp.compute_ctl_config))
Ok(Some(spec))
} else {
bail!("compute is attached, but spec is empty")
}
@@ -122,10 +121,10 @@ pub fn get_spec_from_control_plane(
}
};
if let Err(e) = &result {
if let Err(e) = &spec {
error!("attempt {} to get spec failed with: {}", attempt, e);
} else {
return result;
return spec;
}
attempt += 1;
@@ -133,14 +132,13 @@ pub fn get_spec_from_control_plane(
}
// All attempts failed, return error.
Err(anyhow::anyhow!(
"Exhausted all attempts to retrieve the spec from the control plane"
))
spec
}
/// Check `pg_hba.conf` and update if needed to allow external connections.
pub fn update_pg_hba(pgdata_path: &Path) -> Result<()> {
// XXX: consider making it a part of spec.json
info!("checking pg_hba.conf");
let pghba_path = pgdata_path.join("pg_hba.conf");
if config::line_in_file(&pghba_path, PG_HBA_ALL_MD5)? {
@@ -155,11 +153,12 @@ pub fn update_pg_hba(pgdata_path: &Path) -> Result<()> {
/// Create a standby.signal file
pub fn add_standby_signal(pgdata_path: &Path) -> Result<()> {
// XXX: consider making it a part of spec.json
info!("adding standby.signal");
let signalfile = pgdata_path.join("standby.signal");
if !signalfile.exists() {
File::create(signalfile)?;
info!("created standby.signal");
File::create(signalfile)?;
} else {
info!("reused pre-existing standby.signal");
}
@@ -168,6 +167,7 @@ pub fn add_standby_signal(pgdata_path: &Path) -> Result<()> {
#[instrument(skip_all)]
pub async fn handle_neon_extension_upgrade(client: &mut Client) -> Result<()> {
info!("handle neon extension upgrade");
let query = "ALTER EXTENSION neon UPDATE";
info!("update neon extension version with query: {}", query);
client.simple_query(query).await?;

View File

@@ -1,18 +1,18 @@
use std::collections::{HashMap, HashSet};
use std::fmt::{Debug, Formatter};
use std::future::Future;
use std::iter::{empty, once};
use std::iter::empty;
use std::iter::once;
use std::sync::Arc;
use anyhow::Result;
use crate::compute::construct_superuser_query;
use crate::pg_helpers::{escape_literal, DatabaseExt, Escaping, GenericOptionsSearch, RoleExt};
use anyhow::{bail, Result};
use compute_api::spec::{ComputeFeature, ComputeSpec, Database, PgIdent, Role};
use futures::future::join_all;
use tokio::sync::RwLock;
use tokio_postgres::Client;
use tracing::{Instrument, debug, info_span, warn};
use crate::compute::construct_superuser_query;
use crate::pg_helpers::{DatabaseExt, Escaping, GenericOptionsSearch, RoleExt, escape_literal};
use tracing::{debug, info_span, Instrument};
#[derive(Clone)]
pub enum DB {
@@ -47,11 +47,6 @@ pub enum PerDatabasePhase {
DeleteDBRoleReferences,
ChangeSchemaPerms,
HandleAnonExtension,
/// This is a shared phase, used for both i) dropping dangling LR subscriptions
/// before dropping the DB, and ii) dropping all subscriptions after creating
/// a fresh branch.
/// N.B. we will skip all DBs that are not present in Postgres, invalid, or
/// have `datallowconn = false` (`restrict_conn`).
DropLogicalSubscriptions,
}
@@ -173,7 +168,7 @@ where
///
/// In the future we may generate a single stream of changes and then
/// sort/merge/batch execution, but for now this is a nice way to improve
/// batching behavior of the commands.
/// batching behaviour of the commands.
async fn get_operations<'a>(
spec: &'a ComputeSpec,
ctx: &'a RwLock<MutableApplyContext>,
@@ -456,41 +451,6 @@ async fn get_operations<'a>(
)),
}))),
ApplySpecPhase::RunInEachDatabase { db, subphase } => {
// Do some checks that user DB exists and we can access it.
//
// During the phases like DropLogicalSubscriptions, DeleteDBRoleReferences,
// which happen before dropping the DB, the current run could be a retry,
// so it's a valid case when DB is absent already. The case of
// `pg_database.datallowconn = false`/`restrict_conn` is a bit tricky, as
// in theory user can have some dangling objects there, so we will fail at
// the actual drop later. Yet, to fix that in the current code we would need
// to ALTER DATABASE, and then check back, but that even more invasive, so
// that's not what we really want to do here.
//
// For ChangeSchemaPerms, skipping DBs we cannot access is totally fine.
if let DB::UserDB(db) = db {
let databases = &ctx.read().await.dbs;
let edb = match databases.get(&db.name) {
Some(edb) => edb,
None => {
warn!(
"skipping RunInEachDatabase phase {:?}, database {} doesn't exist in PostgreSQL",
subphase, db.name
);
return Ok(Box::new(empty()));
}
};
if edb.restrict_conn || edb.invalid {
warn!(
"skipping RunInEachDatabase phase {:?}, database {} is (restrict_conn={}, invalid={})",
subphase, db.name, edb.restrict_conn, edb.invalid
);
return Ok(Box::new(empty()));
}
}
match subphase {
PerDatabasePhase::DropLogicalSubscriptions => {
match &db {
@@ -570,12 +530,25 @@ async fn get_operations<'a>(
Ok(Box::new(operations))
}
PerDatabasePhase::ChangeSchemaPerms => {
let ctx = ctx.read().await;
let databases = &ctx.dbs;
let db = match &db {
// ignore schema permissions on the system database
DB::SystemDB => return Ok(Box::new(empty())),
DB::UserDB(db) => db,
};
if databases.get(&db.name).is_none() {
bail!("database {} doesn't exist in PostgreSQL", db.name);
}
let edb = databases.get(&db.name).unwrap();
if edb.restrict_conn || edb.invalid {
return Ok(Box::new(empty()));
}
let operations = vec![
Operation {
query: format!(
@@ -593,7 +566,6 @@ async fn get_operations<'a>(
Ok(Box::new(operations))
}
// TODO: remove this completely https://github.com/neondatabase/cloud/issues/22663
PerDatabasePhase::HandleAnonExtension => {
// Only install Anon into user databases
let db = match &db {

View File

@@ -2,7 +2,6 @@ DO $$
DECLARE
subname TEXT;
BEGIN
LOCK TABLE pg_subscription IN ACCESS EXCLUSIVE MODE;
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);

View File

@@ -1,11 +1,10 @@
use std::path::Path;
use anyhow::{Context, anyhow};
use tracing::{instrument, warn};
use anyhow::{anyhow, Context};
use tracing::warn;
pub const RESIZE_SWAP_BIN: &str = "/neonvm/bin/resize-swap";
#[instrument]
pub fn resize_swap(size_bytes: u64) -> anyhow::Result<()> {
// run `/neonvm/bin/resize-swap --once {size_bytes}`
//

View File

@@ -1,7 +1,7 @@
#[cfg(test)]
mod config_tests {
use std::fs::{File, remove_file};
use std::fs::{remove_file, File};
use std::io::{Read, Write};
use std::path::Path;

View File

@@ -887,6 +887,20 @@ fn print_timeline(
Ok(())
}
/// Returns a map of timeline IDs to timeline_id@lsn strings.
/// Connects to the pageserver to query this information.
async fn get_timeline_infos(
env: &local_env::LocalEnv,
tenant_shard_id: &TenantShardId,
) -> Result<HashMap<TimelineId, TimelineInfo>> {
Ok(get_default_pageserver(env)
.timeline_list(tenant_shard_id)
.await?
.into_iter()
.map(|timeline_info| (timeline_info.timeline_id, timeline_info))
.collect())
}
/// Helper function to get tenant id from an optional --tenant_id option or from the config file
fn get_tenant_id(
tenant_id_arg: Option<TenantId>,
@@ -1237,6 +1251,12 @@ async fn handle_endpoint(subcmd: &EndpointCmd, env: &local_env::LocalEnv) -> Res
// TODO(sharding): this command shouldn't have to specify a shard ID: we should ask the storage controller
// where shard 0 is attached, and query there.
let tenant_shard_id = get_tenant_shard_id(args.tenant_shard_id, env)?;
let timeline_infos = get_timeline_infos(env, &tenant_shard_id)
.await
.unwrap_or_else(|e| {
eprintln!("Failed to load timeline info: {}", e);
HashMap::new()
});
let timeline_name_mappings = env.timeline_name_mappings();
@@ -1265,9 +1285,12 @@ async fn handle_endpoint(subcmd: &EndpointCmd, env: &local_env::LocalEnv) -> Res
lsn.to_string()
}
_ => {
// As the LSN here refers to the one that the compute is started with,
// we display nothing as it is a primary/hot standby compute.
"---".to_string()
// -> primary endpoint or hot replica
// Use the LSN at the end of the timeline.
timeline_infos
.get(&endpoint.timeline_id)
.map(|bi| bi.last_record_lsn.to_string())
.unwrap_or_else(|| "?".to_string())
}
};

View File

@@ -46,12 +46,8 @@ use std::process::Command;
use std::str::FromStr;
use std::sync::Arc;
use std::time::Duration;
use std::time::SystemTime;
use std::time::UNIX_EPOCH;
use anyhow::{anyhow, bail, Context, Result};
use compute_api::requests::ConfigurationRequest;
use compute_api::responses::ComputeCtlConfig;
use compute_api::spec::Database;
use compute_api::spec::PgIdent;
use compute_api::spec::RemoteExtSpec;
@@ -61,7 +57,6 @@ use nix::sys::signal::Signal;
use pageserver_api::shard::ShardStripeSize;
use reqwest::header::CONTENT_TYPE;
use serde::{Deserialize, Serialize};
use tracing::debug;
use url::Host;
use utils::id::{NodeId, TenantId, TimelineId};
@@ -84,10 +79,8 @@ pub struct EndpointConf {
internal_http_port: u16,
pg_version: u32,
skip_pg_catalog_updates: bool,
reconfigure_concurrency: usize,
drop_subscriptions_before_start: bool,
features: Vec<ComputeFeature>,
cluster: Option<Cluster>,
}
//
@@ -184,9 +177,7 @@ impl ComputeControlPlane {
// we also skip catalog updates in the cloud.
skip_pg_catalog_updates,
drop_subscriptions_before_start,
reconfigure_concurrency: 1,
features: vec![],
cluster: None,
});
ep.create_endpoint_dir()?;
@@ -203,9 +194,7 @@ impl ComputeControlPlane {
pg_version,
skip_pg_catalog_updates,
drop_subscriptions_before_start,
reconfigure_concurrency: 1,
features: vec![],
cluster: None,
})?,
)?;
std::fs::write(
@@ -270,11 +259,8 @@ pub struct Endpoint {
skip_pg_catalog_updates: bool,
drop_subscriptions_before_start: bool,
reconfigure_concurrency: usize,
// Feature flags
features: Vec<ComputeFeature>,
// Cluster settings
cluster: Option<Cluster>,
}
#[derive(PartialEq, Eq)]
@@ -314,8 +300,6 @@ impl Endpoint {
let conf: EndpointConf =
serde_json::from_slice(&std::fs::read(entry.path().join("endpoint.json"))?)?;
debug!("serialized endpoint conf: {:?}", conf);
Ok(Endpoint {
pg_address: SocketAddr::new(IpAddr::from(Ipv4Addr::LOCALHOST), conf.pg_port),
external_http_address: SocketAddr::new(
@@ -333,10 +317,8 @@ impl Endpoint {
tenant_id: conf.tenant_id,
pg_version: conf.pg_version,
skip_pg_catalog_updates: conf.skip_pg_catalog_updates,
reconfigure_concurrency: conf.reconfigure_concurrency,
drop_subscriptions_before_start: conf.drop_subscriptions_before_start,
features: conf.features,
cluster: conf.cluster,
})
}
@@ -623,7 +605,7 @@ impl Endpoint {
};
// Create spec file
let mut spec = ComputeSpec {
let spec = ComputeSpec {
skip_pg_catalog_updates: self.skip_pg_catalog_updates,
format_version: 1.0,
operation_uuid: None,
@@ -656,7 +638,7 @@ impl Endpoint {
Vec::new()
},
settings: None,
postgresql_conf: Some(postgresql_conf.clone()),
postgresql_conf: Some(postgresql_conf),
},
delta_operations: None,
tenant_id: Some(self.tenant_id),
@@ -669,35 +651,9 @@ impl Endpoint {
pgbouncer_settings: None,
shard_stripe_size: Some(shard_stripe_size),
local_proxy_config: None,
reconfigure_concurrency: self.reconfigure_concurrency,
reconfigure_concurrency: 1,
drop_subscriptions_before_start: self.drop_subscriptions_before_start,
};
// this strange code is needed to support respec() in tests
if self.cluster.is_some() {
debug!("Cluster is already set in the endpoint spec, using it");
spec.cluster = self.cluster.clone().unwrap();
debug!("spec.cluster {:?}", spec.cluster);
// fill missing fields again
if create_test_user {
spec.cluster.roles.push(Role {
name: PgIdent::from_str("test").unwrap(),
encrypted_password: None,
options: None,
});
spec.cluster.databases.push(Database {
name: PgIdent::from_str("neondb").unwrap(),
owner: PgIdent::from_str("test").unwrap(),
options: None,
restrict_conn: false,
invalid: false,
});
}
spec.cluster.postgresql_conf = Some(postgresql_conf);
}
let spec_path = self.endpoint_path().join("spec.json");
std::fs::write(spec_path, serde_json::to_string_pretty(&spec)?)?;
@@ -715,14 +671,18 @@ impl Endpoint {
println!("Also at '{}'", conn_str);
}
let mut cmd = Command::new(self.env.neon_distrib_dir.join("compute_ctl"));
//cmd.args([
// "--external-http-port",
// &self.external_http_address.port().to_string(),
//])
//.args([
// "--internal-http-port",
// &self.internal_http_address.port().to_string(),
//])
cmd.args([
"--external-http-port",
"--http-port",
&self.external_http_address.port().to_string(),
])
.args([
"--internal-http-port",
&self.internal_http_address.port().to_string(),
])
.args(["--pgdata", self.pgdata().to_str().unwrap()])
.args(["--connstr", &conn_str])
.args([
@@ -739,16 +699,20 @@ impl Endpoint {
])
// TODO: It would be nice if we generated compute IDs with the same
// algorithm as the real control plane.
.args([
"--compute-id",
&format!(
"compute-{}",
SystemTime::now()
.duration_since(UNIX_EPOCH)
.unwrap()
.as_secs()
),
])
//
// TODO: Add this back when
// https://github.com/neondatabase/neon/pull/10747 is merged.
//
//.args([
// "--compute-id",
// &format!(
// "compute-{}",
// SystemTime::now()
// .duration_since(UNIX_EPOCH)
// .unwrap()
// .as_secs()
// ),
//])
.stdin(std::process::Stdio::null())
.stderr(logfile.try_clone()?)
.stdout(logfile);
@@ -916,13 +880,10 @@ impl Endpoint {
self.external_http_address.port()
))
.header(CONTENT_TYPE.as_str(), "application/json")
.body(
serde_json::to_string(&ConfigurationRequest {
spec,
compute_ctl_config: ComputeCtlConfig::default(),
})
.unwrap(),
)
.body(format!(
"{{\"spec\":{}}}",
serde_json::to_string_pretty(&spec)?
))
.send()
.await?;

View File

@@ -335,21 +335,13 @@ impl PageServerNode {
.map(|x| x.parse::<u64>())
.transpose()
.context("Failed to parse 'checkpoint_distance' as an integer")?,
checkpoint_timeout: settings
.remove("checkpoint_timeout")
.map(humantime::parse_duration)
.transpose()
.context("Failed to parse 'checkpoint_timeout' as duration")?,
checkpoint_timeout: settings.remove("checkpoint_timeout").map(|x| x.to_string()),
compaction_target_size: settings
.remove("compaction_target_size")
.map(|x| x.parse::<u64>())
.transpose()
.context("Failed to parse 'compaction_target_size' as an integer")?,
compaction_period: settings
.remove("compaction_period")
.map(humantime::parse_duration)
.transpose()
.context("Failed to parse 'compaction_period' as duration")?,
compaction_period: settings.remove("compaction_period").map(|x| x.to_string()),
compaction_threshold: settings
.remove("compaction_threshold")
.map(|x| x.parse::<usize>())
@@ -395,10 +387,7 @@ impl PageServerNode {
.map(|x| x.parse::<u64>())
.transpose()
.context("Failed to parse 'gc_horizon' as an integer")?,
gc_period: settings.remove("gc_period")
.map(humantime::parse_duration)
.transpose()
.context("Failed to parse 'gc_period' as duration")?,
gc_period: settings.remove("gc_period").map(|x| x.to_string()),
image_creation_threshold: settings
.remove("image_creation_threshold")
.map(|x| x.parse::<usize>())
@@ -414,20 +403,13 @@ impl PageServerNode {
.map(|x| x.parse::<usize>())
.transpose()
.context("Failed to parse 'image_creation_preempt_threshold' as integer")?,
pitr_interval: settings.remove("pitr_interval")
.map(humantime::parse_duration)
.transpose()
.context("Failed to parse 'pitr_interval' as duration")?,
pitr_interval: settings.remove("pitr_interval").map(|x| x.to_string()),
walreceiver_connect_timeout: settings
.remove("walreceiver_connect_timeout")
.map(humantime::parse_duration)
.transpose()
.context("Failed to parse 'walreceiver_connect_timeout' as duration")?,
.map(|x| x.to_string()),
lagging_wal_timeout: settings
.remove("lagging_wal_timeout")
.map(humantime::parse_duration)
.transpose()
.context("Failed to parse 'lagging_wal_timeout' as duration")?,
.map(|x| x.to_string()),
max_lsn_wal_lag: settings
.remove("max_lsn_wal_lag")
.map(|x| x.parse::<NonZeroU64>())
@@ -445,14 +427,8 @@ impl PageServerNode {
.context("Failed to parse 'min_resident_size_override' as integer")?,
evictions_low_residence_duration_metric_threshold: settings
.remove("evictions_low_residence_duration_metric_threshold")
.map(humantime::parse_duration)
.transpose()
.context("Failed to parse 'evictions_low_residence_duration_metric_threshold' as duration")?,
heatmap_period: settings
.remove("heatmap_period")
.map(humantime::parse_duration)
.transpose()
.context("Failed to parse 'heatmap_period' as duration")?,
.map(|x| x.to_string()),
heatmap_period: settings.remove("heatmap_period").map(|x| x.to_string()),
lazy_slru_download: settings
.remove("lazy_slru_download")
.map(|x| x.parse::<bool>())
@@ -463,15 +439,10 @@ impl PageServerNode {
.map(serde_json::from_str)
.transpose()
.context("parse `timeline_get_throttle` from json")?,
lsn_lease_length: settings.remove("lsn_lease_length")
.map(humantime::parse_duration)
.transpose()
.context("Failed to parse 'lsn_lease_length' as duration")?,
lsn_lease_length: settings.remove("lsn_lease_length").map(|x| x.to_string()),
lsn_lease_length_for_ts: settings
.remove("lsn_lease_length_for_ts")
.map(humantime::parse_duration)
.transpose()
.context("Failed to parse 'lsn_lease_length_for_ts' as duration")?,
.map(|x| x.to_string()),
timeline_offloading: settings
.remove("timeline_offloading")
.map(|x| x.parse::<bool>())

View File

@@ -838,10 +838,7 @@ impl StorageController {
self.dispatch(
Method::PUT,
format!("control/v1/tenant/{tenant_shard_id}/migrate"),
Some(TenantShardMigrateRequest {
node_id,
migration_config: None,
}),
Some(TenantShardMigrateRequest { node_id }),
)
.await
}

View File

@@ -22,7 +22,7 @@ use pageserver_api::{
};
use pageserver_client::mgmt_api::{self};
use reqwest::{Method, StatusCode, Url};
use utils::id::{NodeId, TenantId, TimelineId};
use utils::id::{NodeId, TenantId};
use pageserver_api::controller_api::{
NodeConfigureRequest, NodeRegisterRequest, NodeSchedulingPolicy, PlacementPolicy,
@@ -47,9 +47,6 @@ enum Command {
listen_http_addr: String,
#[arg(long)]
listen_http_port: u16,
#[arg(long)]
listen_https_port: Option<u16>,
#[arg(long)]
availability_zone_id: String,
},
@@ -242,19 +239,6 @@ enum Command {
#[arg(long)]
scheduling_policy: SkSchedulingPolicyArg,
},
/// Downloads any missing heatmap layers for all shard for a given timeline
DownloadHeatmapLayers {
/// Tenant ID or tenant shard ID. When an unsharded tenant ID is specified,
/// the operation is performed on all shards. When a sharded tenant ID is
/// specified, the operation is only performed on the specified shard.
#[arg(long)]
tenant_shard_id: TenantShardId,
#[arg(long)]
timeline_id: TimelineId,
/// Optional: Maximum download concurrency (default is 16)
#[arg(long)]
concurrency: Option<usize>,
},
}
#[derive(Parser)]
@@ -397,7 +381,6 @@ async fn main() -> anyhow::Result<()> {
listen_pg_port,
listen_http_addr,
listen_http_port,
listen_https_port,
availability_zone_id,
} => {
storcon_client
@@ -410,7 +393,6 @@ async fn main() -> anyhow::Result<()> {
listen_pg_port,
listen_http_addr,
listen_http_port,
listen_https_port,
availability_zone_id: AvailabilityZone(availability_zone_id),
}),
)
@@ -627,10 +609,7 @@ async fn main() -> anyhow::Result<()> {
tenant_shard_id,
node,
} => {
let req = TenantShardMigrateRequest {
node_id: node,
migration_config: None,
};
let req = TenantShardMigrateRequest { node_id: node };
storcon_client
.dispatch::<TenantShardMigrateRequest, TenantShardMigrateResponse>(
@@ -644,10 +623,7 @@ async fn main() -> anyhow::Result<()> {
tenant_shard_id,
node,
} => {
let req = TenantShardMigrateRequest {
node_id: node,
migration_config: None,
};
let req = TenantShardMigrateRequest { node_id: node };
storcon_client
.dispatch::<TenantShardMigrateRequest, TenantShardMigrateResponse>(
@@ -959,7 +935,7 @@ async fn main() -> anyhow::Result<()> {
threshold: threshold.into(),
},
)),
heatmap_period: Some(Duration::from_secs(300)),
heatmap_period: Some("300s".to_string()),
..Default::default()
},
})
@@ -1106,10 +1082,7 @@ async fn main() -> anyhow::Result<()> {
.dispatch::<TenantShardMigrateRequest, TenantShardMigrateResponse>(
Method::PUT,
format!("control/v1/tenant/{}/migrate", mv.tenant_shard_id),
Some(TenantShardMigrateRequest {
node_id: mv.to,
migration_config: None,
}),
Some(TenantShardMigrateRequest { node_id: mv.to }),
)
.await
.map_err(|e| (mv.tenant_shard_id, mv.from, mv.to, e))
@@ -1265,24 +1238,6 @@ async fn main() -> anyhow::Result<()> {
String::from(scheduling_policy)
);
}
Command::DownloadHeatmapLayers {
tenant_shard_id,
timeline_id,
concurrency,
} => {
let mut path = format!(
"/v1/tenant/{}/timeline/{}/download_heatmap_layers",
tenant_shard_id, timeline_id,
);
if let Some(c) = concurrency {
path = format!("{path}?concurrency={c}");
}
storcon_client
.dispatch::<(), ()>(Method::POST, path, None)
.await?;
}
}
Ok(())

View File

@@ -77,5 +77,4 @@ echo "Start compute node"
/usr/local/bin/compute_ctl --pgdata /var/db/postgres/compute \
-C "postgresql://cloud_admin@localhost:55433/postgres" \
-b /usr/local/bin/postgres \
--compute-id "compute-$RANDOM" \
-S ${SPEC_FILE}

View File

@@ -51,6 +51,8 @@ for pg_version in ${TEST_VERSION_ONLY-14 15 16 17}; do
done
if [ $pg_version -ge 16 ]; then
docker cp ext-src $TEST_CONTAINER_NAME:/
docker exec $TEST_CONTAINER_NAME bash -c "apt update && apt install -y libtap-parser-sourcehandler-pgtap-perl"
# This is required for the pg_hint_plan test, to prevent flaky log message causing the test to fail
# It cannot be moved to Dockerfile now because the database directory is created after the start of the container
echo Adding dummy config
@@ -69,7 +71,7 @@ for pg_version in ${TEST_VERSION_ONLY-14 15 16 17}; do
cat ../compute/patches/contrib_pg${pg_version}.patch | docker exec -i $TEST_CONTAINER_NAME bash -c "(cd /postgres && patch -p1)"
# We are running tests now
rm -f testout.txt testout_contrib.txt
docker exec -e USE_PGXS=1 -e SKIP=timescaledb-src,rdkit-src,postgis-src,pgx_ulid-src,pg_tiktoken-src,pg_jsonschema-src,kq_imcx-src,wal2json_2_5-src \
docker exec -e USE_PGXS=1 -e SKIP=timescaledb-src,rdkit-src,postgis-src,pgx_ulid-src,pgtap-src,pg_tiktoken-src,pg_jsonschema-src,kq_imcx-src,wal2json_2_5-src \
$TEST_CONTAINER_NAME /run-tests.sh /ext-src | tee testout.txt && EXT_SUCCESS=1 || EXT_SUCCESS=0
docker exec -e SKIP=start-scripts,postgres_fdw,ltree_plpython,jsonb_plpython,jsonb_plperl,hstore_plpython,hstore_plperl,dblink,bool_plperl \
$TEST_CONTAINER_NAME /run-tests.sh /postgres/contrib | tee testout_contrib.txt && CONTRIB_SUCCESS=1 || CONTRIB_SUCCESS=0
@@ -79,8 +81,15 @@ for pg_version in ${TEST_VERSION_ONLY-14 15 16 17}; do
[ $EXT_SUCCESS -eq 0 ] && FAILED=$(tail -1 testout.txt | awk '{for(i=1;i<=NF;i++){print "/ext-src/"$i;}}')
[ $CONTRIB_SUCCESS -eq 0 ] && CONTRIB_FAILED=$(tail -1 testout_contrib.txt | awk '{for(i=0;i<=NF;i++){print "/postgres/contrib/"$i;}}')
for d in $FAILED $CONTRIB_FAILED; do
docker exec $TEST_CONTAINER_NAME bash -c 'for file in $(find '"$d"' -name regression.diffs -o -name regression.out); do cat $file; done' || [ $? -eq 1 ]
dn="$(basename $d)"
rm -rf $dn
mkdir $dn
docker cp $TEST_CONTAINER_NAME:$d/regression.diffs $dn || [ $? -eq 1 ]
docker cp $TEST_CONTAINER_NAME:$d/regression.out $dn || [ $? -eq 1 ]
cat $dn/regression.out $dn/regression.diffs || true
rm -rf $dn
done
rm -rf $FAILED
exit 1
fi
fi

View File

@@ -1,5 +0,0 @@
#!/bin/sh
set -ex
cd "$(dirname ${0})"
PG_REGRESS=$(dirname "$(pg_config --pgxs)")/../test/regress/pg_regress
${PG_REGRESS} --use-existing --inputdir=./regress --bindir='/usr/local/pgsql/bin' --dbname=contrib_regression repack-setup repack-run error-on-invalid-idx no-error-on-invalid-idx after-schema repack-check nosuper get_order_by trigger

View File

@@ -1,24 +0,0 @@
diff --git a/test/sql/base.sql b/test/sql/base.sql
index 53adb30..2eed91b 100644
--- a/test/sql/base.sql
+++ b/test/sql/base.sql
@@ -2,7 +2,6 @@
BEGIN;
\i test/pgtap-core.sql
-CREATE EXTENSION semver;
SELECT plan(334);
--SELECT * FROM no_plan();
diff --git a/test/sql/corpus.sql b/test/sql/corpus.sql
index c0fe98e..39cdd2e 100644
--- a/test/sql/corpus.sql
+++ b/test/sql/corpus.sql
@@ -4,7 +4,6 @@ BEGIN;
-- Test the SemVer corpus from https://regex101.com/r/Ly7O1x/3/.
\i test/pgtap-core.sql
-CREATE EXTENSION semver;
SELECT plan(76);
--SELECT * FROM no_plan();

View File

@@ -1,7 +1,6 @@
#!/bin/sh
set -ex
cd "$(dirname ${0})"
patch -p1 <test-upgrade-${PG_VERSION}.patch
psql -d contrib_regression -c "DROP EXTENSION IF EXISTS pgtap"
patch -p1 <test-upgrade.patch
PG_REGRESS=$(dirname "$(pg_config --pgxs)")/../test/regress/pg_regress
${PG_REGRESS} --use-existing --inputdir=./ --bindir='/usr/local/pgsql/bin' --inputdir=test --dbname=contrib_regression base corpus

View File

@@ -1,28 +0,0 @@
diff --git a/Makefile b/Makefile
index f255fe6..0a0fa65 100644
--- a/Makefile
+++ b/Makefile
@@ -346,7 +346,7 @@ test: test-serial test-parallel
TB_DIR = test/build
GENERATED_SCHEDULE_DEPS = $(TB_DIR)/all_tests $(TB_DIR)/exclude_tests
REGRESS = --schedule $(TB_DIR)/run.sch # Set this again just to be safe
-REGRESS_OPTS = --inputdir=test --max-connections=$(PARALLEL_CONN) --schedule $(SETUP_SCH) $(REGRESS_CONF)
+REGRESS_OPTS = --use-existing --dbname=pgtap_regression --inputdir=test --max-connections=$(PARALLEL_CONN) --schedule $(SETUP_SCH) $(REGRESS_CONF)
SETUP_SCH = test/schedule/main.sch # schedule to use for test setup; this can be forcibly changed by some targets!
IGNORE_TESTS = $(notdir $(EXCLUDE_TEST_FILES:.sql=))
PARALLEL_TESTS = $(filter-out $(IGNORE_TESTS),$(filter-out $(SERIAL_TESTS),$(ALL_TESTS)))
diff --git a/test/schedule/create.sql b/test/schedule/create.sql
index ba355ed..7e250f5 100644
--- a/test/schedule/create.sql
+++ b/test/schedule/create.sql
@@ -1,3 +1,2 @@
\unset ECHO
\i test/psql.sql
-CREATE EXTENSION pgtap;
diff --git a/test/schedule/main.sch b/test/schedule/main.sch
index a8a5fbc..0463fc4 100644
--- a/test/schedule/main.sch
+++ b/test/schedule/main.sch
@@ -1,2 +1 @@
-test: build
test: create

View File

@@ -1,5 +0,0 @@
#!/bin/sh
set -ex
cd "$(dirname ${0})"
patch -p1 <test-upgrade.patch
make installcheck

View File

@@ -2,5 +2,4 @@
set -ex
cd "$(dirname ${0})"
PG_REGRESS=$(dirname "$(pg_config --pgxs)")/../test/regress/pg_regress
REGRESS="$(make -n installcheck | awk '{print substr($0,index($0,"init-extension")+15);}')"
${PG_REGRESS} --inputdir=./ --bindir='/usr/local/pgsql/bin' --use-existing --dbname=contrib_regression ${REGRESS}
${PG_REGRESS} --inputdir=./ --bindir='/usr/local/pgsql/bin' --use-existing --dbname=contrib_regression plv8 plv8-errors scalar_args inline json startup_pre startup varparam json_conv jsonb_conv window guc es6 arraybuffer composites currentresource startup_perms bytea find_function_perms memory_limits reset show array_spread regression dialect bigint procedure

View File

@@ -11,7 +11,6 @@ if [ -z ${OLDTAG+x} ] || [ -z ${NEWTAG+x} ] || [ -z "${OLDTAG}" ] || [ -z "${NEW
exit 1
fi
export PG_VERSION=${PG_VERSION:-16}
export PG_TEST_VERSION=${PG_VERSION}
function wait_for_ready {
TIME=0
while ! docker compose logs compute_is_ready | grep -q "accepting connections" && [ ${TIME} -le 300 ] ; do
@@ -42,9 +41,7 @@ EXTENSIONS='[
{"extname": "roaringbitmap", "extdir": "pg_roaringbitmap-src"},
{"extname": "semver", "extdir": "pg_semver-src"},
{"extname": "pg_ivm", "extdir": "pg_ivm-src"},
{"extname": "pgjwt", "extdir": "pgjwt-src"},
{"extname": "pgtap", "extdir": "pgtap-src"},
{"extname": "pg_repack", "extdir": "pg_repack-src"}
{"extname": "pgjwt", "extdir": "pgjwt-src"}
]'
EXTNAMES=$(echo ${EXTENSIONS} | jq -r '.[].extname' | paste -sd ' ' -)
TAG=${NEWTAG} docker compose --profile test-extensions up --quiet-pull --build -d
@@ -57,17 +54,12 @@ new_vers=$(docker compose exec neon-test-extensions psql -Aqt -d contrib_regress
docker compose --profile test-extensions down
TAG=${OLDTAG} docker compose --profile test-extensions up --quiet-pull --build -d --force-recreate
wait_for_ready
docker compose cp ext-src neon-test-extensions:/
docker compose exec neon-test-extensions psql -c "DROP DATABASE IF EXISTS contrib_regression"
docker compose exec neon-test-extensions psql -c "CREATE DATABASE contrib_regression"
docker compose exec neon-test-extensions psql -c "CREATE DATABASE pgtap_regression"
docker compose exec neon-test-extensions psql -d pgtap_regression -c "CREATE EXTENSION pgtap"
create_extensions "${EXTNAMES}"
if [ "${FORCE_ALL_UPGRADE_TESTS:-false}" = true ]; then
exts="${EXTNAMES}"
else
query="select pge.extname from pg_extension pge join (select key as extname, value as extversion from json_each_text('${new_vers}')) x on pge.extname=x.extname and pge.extversion <> x.extversion"
exts=$(docker compose exec neon-test-extensions psql -Aqt -d contrib_regression -c "$query")
fi
query="select pge.extname from pg_extension pge join (select key as extname, value as extversion from json_each_text('${new_vers}')) x on pge.extname=x.extname and pge.extversion <> x.extversion"
exts=$(docker compose exec neon-test-extensions psql -Aqt -d contrib_regression -c "$query")
if [ -z "${exts}" ]; then
echo "No extensions were upgraded"
else
@@ -95,10 +87,7 @@ else
exit 1
fi
docker compose exec neon-test-extensions psql -d contrib_regression -c "\dx ${ext}"
if ! docker compose exec neon-test-extensions sh -c /ext-src/${EXTDIR}/test-upgrade.sh; then
docker compose exec neon-test-extensions cat /ext-src/${EXTDIR}/regression.diffs
exit 1
fi
docker compose exec neon-test-extensions sh -c /ext-src/${EXTDIR}/test-upgrade.sh
docker compose exec neon-test-extensions psql -d contrib_regression -c "alter extension ${ext} update"
docker compose exec neon-test-extensions psql -d contrib_regression -c "\dx ${ext}"
done

View File

@@ -1,13 +1,12 @@
[package]
name = "compute_api"
version = "0.1.0"
edition = "2024"
edition.workspace = true
license.workspace = true
[dependencies]
anyhow.workspace = true
chrono.workspace = true
jsonwebtoken.workspace = true
serde.workspace = true
serde_json.workspace = true
regex.workspace = true

View File

@@ -1,19 +1,18 @@
//! Structs representing the JSON formats used in the compute_ctl's HTTP API.
use serde::{Deserialize, Serialize};
use crate::privilege::Privilege;
use crate::responses::ComputeCtlConfig;
use crate::spec::{ComputeSpec, ExtVersion, PgIdent};
use crate::{
privilege::Privilege,
spec::{ComputeSpec, ExtVersion, PgIdent},
};
use serde::Deserialize;
/// Request of the /configure API
///
/// We now pass only `spec` in the configuration request, but later we can
/// extend it and something like `restart: bool` or something else. So put
/// `spec` into a struct initially to be more flexible in the future.
#[derive(Debug, Deserialize, Serialize)]
#[derive(Deserialize, Debug)]
pub struct ConfigurationRequest {
pub spec: ComputeSpec,
pub compute_ctl_config: ComputeCtlConfig,
}
#[derive(Deserialize, Debug)]

View File

@@ -3,11 +3,12 @@
use std::fmt::Display;
use chrono::{DateTime, Utc};
use jsonwebtoken::jwk::JwkSet;
use serde::{Deserialize, Serialize, Serializer};
use crate::privilege::Privilege;
use crate::spec::{ComputeSpec, Database, ExtVersion, PgIdent, Role};
use crate::{
privilege::Privilege,
spec::{ComputeSpec, Database, ExtVersion, PgIdent, Role},
};
#[derive(Serialize, Debug, Deserialize)]
pub struct GenericAPIError {
@@ -134,27 +135,13 @@ pub struct CatalogObjects {
pub databases: Vec<Database>,
}
#[derive(Debug, Deserialize, Serialize)]
pub struct ComputeCtlConfig {
pub jwks: JwkSet,
}
impl Default for ComputeCtlConfig {
fn default() -> Self {
Self {
jwks: JwkSet {
keys: Vec::default(),
},
}
}
}
/// Response of the `/computes/{compute_id}/spec` control-plane API.
/// This is not actually a compute API response, so consider moving
/// to a different place.
#[derive(Deserialize, Debug)]
pub struct ControlPlaneSpecResponse {
pub spec: Option<ComputeSpec>,
pub status: ControlPlaneComputeStatus,
pub compute_ctl_config: ComputeCtlConfig,
}
#[derive(Deserialize, Clone, Copy, Debug, PartialEq, Eq)]

View File

@@ -5,12 +5,13 @@
//! and connect it to the storage nodes.
use std::collections::HashMap;
use regex::Regex;
use remote_storage::RemotePath;
use serde::{Deserialize, Serialize};
use utils::id::{TenantId, TimelineId};
use utils::lsn::Lsn;
use regex::Regex;
use remote_storage::RemotePath;
/// String type alias representing Postgres identifier and
/// intended to be used for DB / role names.
pub type PgIdent = String;
@@ -251,7 +252,7 @@ pub enum ComputeMode {
Replica,
}
#[derive(Clone, Debug, Default, Deserialize, Serialize, PartialEq, Eq)]
#[derive(Clone, Debug, Default, Deserialize, Serialize)]
pub struct Cluster {
pub cluster_id: Option<String>,
pub name: Option<String>,
@@ -282,7 +283,7 @@ pub struct DeltaOp {
/// Rust representation of Postgres role info with only those fields
/// that matter for us.
#[derive(Clone, Debug, Deserialize, Serialize, PartialEq, Eq)]
#[derive(Clone, Debug, Deserialize, Serialize)]
pub struct Role {
pub name: PgIdent,
pub encrypted_password: Option<String>,
@@ -291,7 +292,7 @@ pub struct Role {
/// Rust representation of Postgres database info with only those fields
/// that matter for us.
#[derive(Clone, Debug, Deserialize, Serialize, PartialEq, Eq)]
#[derive(Clone, Debug, Deserialize, Serialize)]
pub struct Database {
pub name: PgIdent,
pub owner: PgIdent,
@@ -307,7 +308,7 @@ pub struct Database {
/// Common type representing both SQL statement params with or without value,
/// like `LOGIN` or `OWNER username` in the `CREATE/ALTER ROLE`, and config
/// options like `wal_level = logical`.
#[derive(Clone, Debug, Deserialize, Serialize, PartialEq, Eq)]
#[derive(Clone, Debug, Deserialize, Serialize)]
pub struct GenericOption {
pub name: String,
pub value: Option<String>,
@@ -338,9 +339,8 @@ pub struct JwksSettings {
#[cfg(test)]
mod tests {
use std::fs::File;
use super::*;
use std::fs::File;
#[test]
fn allow_installing_remote_extensions() {

View File

@@ -2,6 +2,7 @@ use anyhow::bail;
use flate2::write::{GzDecoder, GzEncoder};
use flate2::Compression;
use itertools::Itertools as _;
use once_cell::sync::Lazy;
use pprof::protos::{Function, Line, Location, Message as _, Profile};
use regex::Regex;
@@ -57,30 +58,38 @@ pub fn symbolize(mut profile: Profile) -> anyhow::Result<Profile> {
// Resolve the line and function for each location.
backtrace::resolve(loc.address as *mut c_void, |symbol| {
let Some(symbol_name) = symbol.name() else {
let Some(symname) = symbol.name() else {
return;
};
let mut name = symname.to_string();
let function_name = format!("{symbol_name:#}");
let functions_len = functions.len();
let function_id = functions
.entry(function_name)
.or_insert_with_key(|function_name| {
let function_id = functions_len as u64 + 1;
let system_name = String::from_utf8_lossy(symbol_name.as_bytes());
// Strip the Rust monomorphization suffix from the symbol name.
static SUFFIX_REGEX: Lazy<Regex> =
Lazy::new(|| Regex::new("::h[0-9a-f]{16}$").expect("invalid regex"));
if let Some(m) = SUFFIX_REGEX.find(&name) {
name.truncate(m.start());
}
let function_id = match functions.get(&name) {
Some(function) => function.id,
None => {
let id = functions.len() as u64 + 1;
let system_name = String::from_utf8_lossy(symname.as_bytes());
let filename = symbol
.filename()
.map(|path| path.to_string_lossy())
.unwrap_or(Cow::Borrowed(""));
Function {
id: function_id,
name: string_id(function_name),
let function = Function {
id,
name: string_id(&name),
system_name: string_id(&system_name),
filename: string_id(&filename),
..Default::default()
}
})
.id;
};
functions.insert(name, function);
id
}
};
loc.line.push(Line {
function_id,
line: symbol.lineno().unwrap_or(0) as i64,

View File

@@ -1,7 +1,7 @@
[package]
name = "pageserver_api"
version = "0.1.0"
edition = "2024"
edition.workspace = true
license.workspace = true
[features]

View File

@@ -9,18 +9,19 @@ pub const DEFAULT_PG_LISTEN_ADDR: &str = formatcp!("127.0.0.1:{DEFAULT_PG_LISTEN
pub const DEFAULT_HTTP_LISTEN_PORT: u16 = 9898;
pub const DEFAULT_HTTP_LISTEN_ADDR: &str = formatcp!("127.0.0.1:{DEFAULT_HTTP_LISTEN_PORT}");
use std::collections::HashMap;
use std::num::{NonZeroU64, NonZeroUsize};
use std::str::FromStr;
use std::time::Duration;
use postgres_backend::AuthType;
use remote_storage::RemoteStorageConfig;
use serde_with::serde_as;
use utils::logging::LogFormat;
use utils::postgres_client::PostgresClientProtocol;
use std::{
collections::HashMap,
num::{NonZeroU64, NonZeroUsize},
str::FromStr,
time::Duration,
};
use utils::{logging::LogFormat, postgres_client::PostgresClientProtocol};
use crate::models::{ImageCompressionAlgorithm, LsnLease};
use crate::models::ImageCompressionAlgorithm;
use crate::models::LsnLease;
// Certain metadata (e.g. externally-addressable name, AZ) is delivered
// as a separate structure. This information is not neeed by the pageserver
@@ -121,8 +122,6 @@ pub struct ConfigToml {
pub page_service_pipelining: PageServicePipeliningConfig,
pub get_vectored_concurrent_io: GetVectoredConcurrentIo,
pub enable_read_path_debugging: Option<bool>,
#[serde(skip_serializing_if = "Option::is_none")]
pub validate_wal_contiguity: Option<bool>,
}
#[derive(Debug, Clone, PartialEq, Eq, serde::Serialize, serde::Deserialize)]
@@ -352,7 +351,7 @@ pub struct TenantConfigToml {
/// Enable rel_size_v2 for this tenant. Once enabled, the tenant will persist this information into
/// `index_part.json`, and it cannot be reversed.
pub rel_size_v2_enabled: bool,
pub rel_size_v2_enabled: Option<bool>,
// gc-compaction related configs
/// Enable automatic gc-compaction trigger on this tenant.
@@ -366,10 +365,10 @@ pub struct TenantConfigToml {
}
pub mod defaults {
pub use storage_broker::DEFAULT_ENDPOINT as BROKER_DEFAULT_ENDPOINT;
use crate::models::ImageCompressionAlgorithm;
pub use storage_broker::DEFAULT_ENDPOINT as BROKER_DEFAULT_ENDPOINT;
pub const DEFAULT_WAIT_LSN_TIMEOUT: &str = "300 s";
pub const DEFAULT_WAL_REDO_TIMEOUT: &str = "60 s";
@@ -522,7 +521,6 @@ impl Default for ConfigToml {
} else {
None
},
validate_wal_contiguity: None,
}
}
}
@@ -546,11 +544,10 @@ pub mod tenant_conf_defaults {
pub const DEFAULT_COMPACTION_PERIOD: &str = "20 s";
pub const DEFAULT_COMPACTION_THRESHOLD: usize = 10;
// This value needs to be tuned to avoid OOM. We have 3/4*CPUs threads for L0 compaction, that's
// 3/4*16=9 on most of our pageservers. Compacting 20 layers requires about 1 GB memory (could
// be reduced later by optimizing L0 hole calculation to avoid loading all keys into memory). So
// with this config, we can get a maximum peak compaction usage of 9 GB.
pub const DEFAULT_COMPACTION_UPPER_LIMIT: usize = 20;
// This value needs to be tuned to avoid OOM. We have 3/4 of the total CPU threads to do background works, that's 16*3/4=9 on
// most of our pageservers. Compaction ~50 layers requires about 2GB memory (could be reduced later by optimizing L0 hole
// calculation to avoid loading all keys into the memory). So with this config, we can get a maximum peak compaction usage of 18GB.
pub const DEFAULT_COMPACTION_UPPER_LIMIT: usize = 50;
pub const DEFAULT_COMPACTION_L0_FIRST: bool = false;
pub const DEFAULT_COMPACTION_L0_SEMAPHORE: bool = true;
@@ -583,7 +580,7 @@ pub mod tenant_conf_defaults {
// image layers should be created.
pub const DEFAULT_IMAGE_LAYER_CREATION_CHECK_THRESHOLD: u8 = 2;
pub const DEFAULT_GC_COMPACTION_ENABLED: bool = false;
pub const DEFAULT_GC_COMPACTION_INITIAL_THRESHOLD_KB: u64 = 5 * 1024 * 1024; // 5GB
pub const DEFAULT_GC_COMPACTION_INITIAL_THRESHOLD_KB: u64 = 10240000;
pub const DEFAULT_GC_COMPACTION_RATIO_PERCENT: u64 = 100;
}
@@ -636,7 +633,7 @@ impl Default for TenantConfigToml {
lsn_lease_length_for_ts: LsnLease::DEFAULT_LENGTH_FOR_TS,
timeline_offloading: true,
wal_receiver_protocol_override: None,
rel_size_v2_enabled: false,
rel_size_v2_enabled: None,
gc_compaction_enabled: DEFAULT_GC_COMPACTION_ENABLED,
gc_compaction_initial_threshold_kb: DEFAULT_GC_COMPACTION_INITIAL_THRESHOLD_KB,
gc_compaction_ratio_percent: DEFAULT_GC_COMPACTION_RATIO_PERCENT,

View File

@@ -9,8 +9,11 @@ use std::time::{Duration, Instant};
use serde::{Deserialize, Serialize};
use utils::id::{NodeId, TenantId};
use crate::models::{PageserverUtilization, ShardParameters, TenantConfig};
use crate::shard::{ShardStripeSize, TenantShardId};
use crate::models::PageserverUtilization;
use crate::{
models::{ShardParameters, TenantConfig},
shard::{ShardStripeSize, TenantShardId},
};
#[derive(Serialize, Deserialize, Debug)]
#[serde(deny_unknown_fields)]
@@ -54,7 +57,6 @@ pub struct NodeRegisterRequest {
pub listen_http_addr: String,
pub listen_http_port: u16,
pub listen_https_port: Option<u16>,
pub availability_zone_id: AvailabilityZone,
}
@@ -103,7 +105,6 @@ pub struct TenantLocateResponseShard {
pub listen_http_addr: String,
pub listen_http_port: u16,
pub listen_https_port: Option<u16>,
}
#[derive(Serialize, Deserialize)]
@@ -147,7 +148,6 @@ pub struct NodeDescribeResponse {
pub listen_http_addr: String,
pub listen_http_port: u16,
pub listen_https_port: Option<u16>,
pub listen_pg_addr: String,
pub listen_pg_port: u16,
@@ -182,18 +182,6 @@ pub struct TenantDescribeResponseShard {
#[derive(Serialize, Deserialize, Debug)]
pub struct TenantShardMigrateRequest {
pub node_id: NodeId,
#[serde(default)]
pub migration_config: Option<MigrationConfig>,
}
#[derive(Serialize, Deserialize, Debug)]
pub struct MigrationConfig {
#[serde(default)]
#[serde(with = "humantime_serde")]
pub secondary_warmup_timeout: Option<Duration>,
#[serde(default)]
#[serde(with = "humantime_serde")]
pub secondary_download_request_timeout: Option<Duration>,
}
#[derive(Serialize, Clone, Debug)]
@@ -351,7 +339,7 @@ impl FromStr for SkSchedulingPolicy {
_ => {
return Err(anyhow::anyhow!(
"Unknown scheduling policy '{s}', try active,pause,decomissioned"
));
))
}
})
}
@@ -454,9 +442,8 @@ pub struct SafekeeperSchedulingPolicyRequest {
#[cfg(test)]
mod test {
use serde_json;
use super::*;
use serde_json;
/// Check stability of PlacementPolicy's serialization
#[test]

View File

@@ -1,13 +1,10 @@
use std::fmt;
use std::ops::Range;
use anyhow::{Result, bail};
use byteorder::{BE, ByteOrder};
use bytes::Bytes;
use anyhow::{bail, Result};
use byteorder::{ByteOrder, BE};
use postgres_ffi::relfile_utils::{FSM_FORKNUM, VISIBILITYMAP_FORKNUM};
use postgres_ffi::{Oid, RepOriginId};
use postgres_ffi::Oid;
use postgres_ffi::RepOriginId;
use serde::{Deserialize, Serialize};
use utils::const_assert;
use std::{fmt, ops::Range};
use crate::reltag::{BlockNumber, RelTag, SlruKind};
@@ -52,64 +49,6 @@ pub const AUX_KEY_PREFIX: u8 = 0x62;
/// The key prefix of ReplOrigin keys.
pub const REPL_ORIGIN_KEY_PREFIX: u8 = 0x63;
/// The key prefix of db directory keys.
pub const DB_DIR_KEY_PREFIX: u8 = 0x64;
/// The key prefix of rel directory keys.
pub const REL_DIR_KEY_PREFIX: u8 = 0x65;
#[derive(Debug, Clone, Copy, Hash, PartialEq, Eq)]
pub enum RelDirExists {
Exists,
Removed,
}
#[derive(Debug)]
pub struct DecodeError;
impl fmt::Display for DecodeError {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
write!(f, "invalid marker")
}
}
impl std::error::Error for DecodeError {}
impl RelDirExists {
/// The value of the rel directory keys that indicates the existence of a relation.
const REL_EXISTS_MARKER: Bytes = Bytes::from_static(b"r");
pub fn encode(&self) -> Bytes {
match self {
Self::Exists => Self::REL_EXISTS_MARKER.clone(),
Self::Removed => SPARSE_TOMBSTONE_MARKER.clone(),
}
}
pub fn decode_option(data: Option<impl AsRef<[u8]>>) -> Result<Self, DecodeError> {
match data {
Some(marker) if marker.as_ref() == Self::REL_EXISTS_MARKER => Ok(Self::Exists),
// Any other marker is invalid
Some(_) => Err(DecodeError),
None => Ok(Self::Removed),
}
}
pub fn decode(data: impl AsRef<[u8]>) -> Result<Self, DecodeError> {
let data = data.as_ref();
if data == Self::REL_EXISTS_MARKER {
Ok(Self::Exists)
} else if data == SPARSE_TOMBSTONE_MARKER {
Ok(Self::Removed)
} else {
Err(DecodeError)
}
}
}
/// A tombstone in the sparse keyspace, which is an empty buffer.
pub const SPARSE_TOMBSTONE_MARKER: Bytes = Bytes::from_static(b"");
/// Check if the key falls in the range of metadata keys.
pub const fn is_metadata_key_slice(key: &[u8]) -> bool {
key[0] >= METADATA_KEY_BEGIN_PREFIX && key[0] < METADATA_KEY_END_PREFIX
@@ -171,24 +110,6 @@ impl Key {
}
}
pub fn rel_dir_sparse_key_range() -> Range<Self> {
Key {
field1: REL_DIR_KEY_PREFIX,
field2: 0,
field3: 0,
field4: 0,
field5: 0,
field6: 0,
}..Key {
field1: REL_DIR_KEY_PREFIX + 1,
field2: 0,
field3: 0,
field4: 0,
field5: 0,
field6: 0,
}
}
/// This function checks more extensively what keys we can take on the write path.
/// If a key beginning with 00 does not have a global/default tablespace OID, it
/// will be rejected on the write path.
@@ -519,36 +440,6 @@ pub fn rel_dir_to_key(spcnode: Oid, dbnode: Oid) -> Key {
}
}
#[inline(always)]
pub fn rel_tag_sparse_key(spcnode: Oid, dbnode: Oid, relnode: Oid, forknum: u8) -> Key {
Key {
field1: REL_DIR_KEY_PREFIX,
field2: spcnode,
field3: dbnode,
field4: relnode,
field5: forknum,
field6: 1,
}
}
pub fn rel_tag_sparse_key_range(spcnode: Oid, dbnode: Oid) -> Range<Key> {
Key {
field1: REL_DIR_KEY_PREFIX,
field2: spcnode,
field3: dbnode,
field4: 0,
field5: 0,
field6: 0,
}..Key {
field1: REL_DIR_KEY_PREFIX,
field2: spcnode,
field3: dbnode,
field4: u32::MAX,
field5: u8::MAX,
field6: u32::MAX,
} // it's fine to exclude the last key b/c we only use field6 == 1
}
#[inline(always)]
pub fn rel_block_to_key(rel: RelTag, blknum: BlockNumber) -> Key {
Key {
@@ -843,9 +734,9 @@ impl Key {
self.field1 == RELATION_SIZE_PREFIX
}
pub const fn sparse_non_inherited_keyspace() -> Range<Key> {
pub fn sparse_non_inherited_keyspace() -> Range<Key> {
// The two keys are adjacent; if we will have non-adjancent keys in the future, we should return a keyspace
const_assert!(AUX_KEY_PREFIX + 1 == REPL_ORIGIN_KEY_PREFIX);
debug_assert_eq!(AUX_KEY_PREFIX + 1, REPL_ORIGIN_KEY_PREFIX);
Key {
field1: AUX_KEY_PREFIX,
field2: 0,
@@ -955,22 +846,25 @@ impl std::str::FromStr for Key {
mod tests {
use std::str::FromStr;
use rand::{Rng, SeedableRng};
use crate::key::is_metadata_key_slice;
use crate::key::Key;
use rand::Rng;
use rand::SeedableRng;
use super::AUX_KEY_PREFIX;
use crate::key::{Key, is_metadata_key_slice};
#[test]
fn display_fromstr_bijection() {
let mut rng = rand::rngs::StdRng::seed_from_u64(42);
let key = Key {
field1: rng.r#gen(),
field2: rng.r#gen(),
field3: rng.r#gen(),
field4: rng.r#gen(),
field5: rng.r#gen(),
field6: rng.r#gen(),
field1: rng.gen(),
field2: rng.gen(),
field3: rng.gen(),
field4: rng.gen(),
field5: rng.gen(),
field6: rng.gen(),
};
assert_eq!(key, Key::from_str(&format!("{key}")).unwrap());

View File

@@ -1,10 +1,11 @@
use postgres_ffi::BLCKSZ;
use std::ops::Range;
use crate::{
key::Key,
shard::{ShardCount, ShardIdentity},
};
use itertools::Itertools;
use postgres_ffi::BLCKSZ;
use crate::key::Key;
use crate::shard::{ShardCount, ShardIdentity};
///
/// Represents a set of Keys, in a compact form.
@@ -26,6 +27,55 @@ impl std::fmt::Display for KeySpace {
}
}
pub struct KeySpaceIter<'a> {
ranges: &'a [Range<Key>],
current_range: usize,
current_key: Option<Key>,
}
impl<'a> Iterator for KeySpaceIter<'a> {
// (current_key, range_end)
type Item = (Key, Key);
fn next(&mut self) -> Option<Self::Item> {
// if we've gone through all ranges, stop iteration
if self.current_range >= self.ranges.len() {
return None;
}
let range = &self.ranges[self.current_range];
// if current_key is None, initialize it with range.start
if self.current_key.is_none() {
self.current_key = Some(range.start);
}
if let Some(current_key) = self.current_key {
// check if the current_key is still within the range
if current_key < range.end {
// get the next key
let next_key = current_key.next();
// move current_key forward
self.current_key = Some(next_key);
// return the range from current_key to the current range_end
return Some((current_key, range.end));
}
}
// move to the next range
self.current_range += 1;
// if there are more ranges, initialize the next key from the start of the next range
if self.current_range < self.ranges.len() {
self.current_key = Some(self.ranges[self.current_range].start);
self.next() // Recurse to continue iterating with the new range
} else {
// no more ranges, end iteration
None
}
}
}
/// A wrapper type for sparse keyspaces.
#[derive(Clone, Debug, Default, PartialEq, Eq)]
pub struct SparseKeySpace(pub KeySpace);
@@ -434,6 +484,14 @@ impl KeySpace {
pub fn contains(&self, key: &Key) -> bool {
self.overlaps(&(*key..key.next()))
}
pub fn iter(&self) -> KeySpaceIter {
KeySpaceIter {
ranges: &self.ranges,
current_range: 0,
current_key: self.ranges.first().map(|r| r.start),
}
}
}
///
@@ -608,13 +666,101 @@ pub fn singleton_range(key: Key) -> Range<Key> {
#[cfg(test)]
mod tests {
use std::fmt::Write;
use rand::{RngCore, SeedableRng};
use crate::{
models::ShardParameters,
shard::{ShardCount, ShardNumber},
};
use super::*;
use crate::models::ShardParameters;
use crate::shard::{ShardCount, ShardNumber};
use std::fmt::Write;
fn key(field1: u8, field2: u32, field6: u32) -> Key {
Key {
field1,
field2,
field3: 0,
field4: 0,
field5: 0,
field6,
}
}
#[test]
fn test_iter_single_range() {
let key_range = Range {
start: key(1, 0, 0),
end: key(1, 0, 5),
};
let keyspace = KeySpace {
ranges: vec![key_range],
};
let collected_ranges: Vec<_> = keyspace.iter().collect();
assert_eq!(
collected_ranges,
vec![
(key(1, 0, 0), key(1, 0, 5)),
(key(1, 0, 1), key(1, 0, 5)),
(key(1, 0, 2), key(1, 0, 5)),
(key(1, 0, 3), key(1, 0, 5)),
(key(1, 0, 4), key(1, 0, 5)), // Stops at field6 = 5
]
);
}
#[test]
fn test_iter_multiple_ranges() {
let ranges = vec![
Range {
start: key(1, 0, 0),
end: key(1, 0, 3),
},
Range {
start: key(2, 0, 0),
end: key(2, 0, 2),
},
];
let keyspace = KeySpace { ranges };
let collected_ranges: Vec<_> = keyspace.iter().collect();
assert_eq!(
collected_ranges,
vec![
(key(1, 0, 0), key(1, 0, 3)),
(key(1, 0, 1), key(1, 0, 3)),
(key(1, 0, 2), key(1, 0, 3)), // End of first range
(key(2, 0, 0), key(2, 0, 2)),
(key(2, 0, 1), key(2, 0, 2)), // End of second range
]
);
}
#[test]
fn test_iter_empty_keyspace() {
let keyspace = KeySpace { ranges: vec![] };
let mut iter = keyspace.iter();
assert_eq!(iter.next(), None);
}
#[test]
fn test_iter_range_with_single_key() {
let key_range = Range {
start: key(1, 42, 0),
end: key(1, 42, 1), // Only one step
};
let keyspace = KeySpace {
ranges: vec![key_range],
};
let mut iter = keyspace.iter();
assert_eq!(iter.next(), Some((key(1, 42, 0), key(1, 42, 1))));
assert_eq!(iter.next(), None);
}
// Helper function to create a key range.
//

View File

@@ -2,30 +2,38 @@ pub mod detach_ancestor;
pub mod partitioning;
pub mod utilization;
use core::ops::Range;
use std::collections::HashMap;
use std::fmt::Display;
use std::io::{BufRead, Read};
use std::num::{NonZeroU32, NonZeroU64, NonZeroUsize};
use std::str::FromStr;
use std::time::{Duration, SystemTime};
use byteorder::{BigEndian, ReadBytesExt};
use bytes::{Buf, BufMut, Bytes, BytesMut};
#[cfg(feature = "testing")]
use camino::Utf8PathBuf;
pub use utilization::PageserverUtilization;
use core::ops::Range;
use std::{
collections::HashMap,
fmt::Display,
io::{BufRead, Read},
num::{NonZeroU32, NonZeroU64, NonZeroUsize},
str::FromStr,
time::{Duration, SystemTime},
};
use byteorder::{BigEndian, ReadBytesExt};
use postgres_ffi::BLCKSZ;
use serde::{Deserialize, Deserializer, Serialize, Serializer};
use serde_with::serde_as;
pub use utilization::PageserverUtilization;
use utils::id::{NodeId, TenantId, TimelineId};
use utils::lsn::Lsn;
use utils::postgres_client::PostgresClientProtocol;
use utils::{completion, serde_system_time};
use utils::{
completion,
id::{NodeId, TenantId, TimelineId},
lsn::Lsn,
postgres_client::PostgresClientProtocol,
serde_system_time,
};
use crate::key::{CompactKey, Key};
use crate::reltag::RelTag;
use crate::shard::{ShardCount, ShardStripeSize, TenantShardId};
use crate::{
key::{CompactKey, Key},
reltag::RelTag,
shard::{ShardCount, ShardStripeSize, TenantShardId},
};
use bytes::{Buf, BufMut, Bytes, BytesMut};
/// The state of a tenant in this pageserver.
///
@@ -324,8 +332,7 @@ pub struct ImportPgdataIdempotencyKey(pub String);
impl ImportPgdataIdempotencyKey {
pub fn random() -> Self {
use rand::Rng;
use rand::distributions::Alphanumeric;
use rand::{distributions::Alphanumeric, Rng};
Self(
rand::thread_rng()
.sample_iter(&Alphanumeric)
@@ -519,13 +526,9 @@ pub struct TenantConfigPatch {
#[derive(Serialize, Deserialize, Debug, Default, Clone, Eq, PartialEq)]
pub struct TenantConfig {
pub checkpoint_distance: Option<u64>,
#[serde(default)]
#[serde(with = "humantime_serde")]
pub checkpoint_timeout: Option<Duration>,
pub checkpoint_timeout: Option<String>,
pub compaction_target_size: Option<u64>,
#[serde(default)]
#[serde(with = "humantime_serde")]
pub compaction_period: Option<Duration>,
pub compaction_period: Option<String>,
pub compaction_threshold: Option<usize>,
pub compaction_upper_limit: Option<usize>,
// defer parsing compaction_algorithm, like eviction_policy
@@ -536,38 +539,22 @@ pub struct TenantConfig {
pub l0_flush_stall_threshold: Option<usize>,
pub l0_flush_wait_upload: Option<bool>,
pub gc_horizon: Option<u64>,
#[serde(default)]
#[serde(with = "humantime_serde")]
pub gc_period: Option<Duration>,
pub gc_period: Option<String>,
pub image_creation_threshold: Option<usize>,
#[serde(default)]
#[serde(with = "humantime_serde")]
pub pitr_interval: Option<Duration>,
#[serde(default)]
#[serde(with = "humantime_serde")]
pub walreceiver_connect_timeout: Option<Duration>,
#[serde(default)]
#[serde(with = "humantime_serde")]
pub lagging_wal_timeout: Option<Duration>,
pub pitr_interval: Option<String>,
pub walreceiver_connect_timeout: Option<String>,
pub lagging_wal_timeout: Option<String>,
pub max_lsn_wal_lag: Option<NonZeroU64>,
pub eviction_policy: Option<EvictionPolicy>,
pub min_resident_size_override: Option<u64>,
#[serde(default)]
#[serde(with = "humantime_serde")]
pub evictions_low_residence_duration_metric_threshold: Option<Duration>,
#[serde(default)]
#[serde(with = "humantime_serde")]
pub heatmap_period: Option<Duration>,
pub evictions_low_residence_duration_metric_threshold: Option<String>,
pub heatmap_period: Option<String>,
pub lazy_slru_download: Option<bool>,
pub timeline_get_throttle: Option<ThrottleConfig>,
pub image_layer_creation_check_threshold: Option<u8>,
pub image_creation_preempt_threshold: Option<usize>,
#[serde(default)]
#[serde(with = "humantime_serde")]
pub lsn_lease_length: Option<Duration>,
#[serde(default)]
#[serde(with = "humantime_serde")]
pub lsn_lease_length_for_ts: Option<Duration>,
pub lsn_lease_length: Option<String>,
pub lsn_lease_length_for_ts: Option<String>,
pub timeline_offloading: Option<bool>,
pub wal_receiver_protocol_override: Option<PostgresClientProtocol>,
pub rel_size_v2_enabled: Option<bool>,
@@ -577,10 +564,7 @@ pub struct TenantConfig {
}
impl TenantConfig {
pub fn apply_patch(
self,
patch: TenantConfigPatch,
) -> Result<TenantConfig, humantime::DurationError> {
pub fn apply_patch(self, patch: TenantConfigPatch) -> TenantConfig {
let Self {
mut checkpoint_distance,
mut checkpoint_timeout,
@@ -620,17 +604,11 @@ impl TenantConfig {
} = self;
patch.checkpoint_distance.apply(&mut checkpoint_distance);
patch
.checkpoint_timeout
.map(|v| humantime::parse_duration(&v))?
.apply(&mut checkpoint_timeout);
patch.checkpoint_timeout.apply(&mut checkpoint_timeout);
patch
.compaction_target_size
.apply(&mut compaction_target_size);
patch
.compaction_period
.map(|v| humantime::parse_duration(&v))?
.apply(&mut compaction_period);
patch.compaction_period.apply(&mut compaction_period);
patch.compaction_threshold.apply(&mut compaction_threshold);
patch
.compaction_upper_limit
@@ -648,25 +626,15 @@ impl TenantConfig {
.apply(&mut l0_flush_stall_threshold);
patch.l0_flush_wait_upload.apply(&mut l0_flush_wait_upload);
patch.gc_horizon.apply(&mut gc_horizon);
patch
.gc_period
.map(|v| humantime::parse_duration(&v))?
.apply(&mut gc_period);
patch.gc_period.apply(&mut gc_period);
patch
.image_creation_threshold
.apply(&mut image_creation_threshold);
patch
.pitr_interval
.map(|v| humantime::parse_duration(&v))?
.apply(&mut pitr_interval);
patch.pitr_interval.apply(&mut pitr_interval);
patch
.walreceiver_connect_timeout
.map(|v| humantime::parse_duration(&v))?
.apply(&mut walreceiver_connect_timeout);
patch
.lagging_wal_timeout
.map(|v| humantime::parse_duration(&v))?
.apply(&mut lagging_wal_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
@@ -674,12 +642,8 @@ impl TenantConfig {
.apply(&mut min_resident_size_override);
patch
.evictions_low_residence_duration_metric_threshold
.map(|v| humantime::parse_duration(&v))?
.apply(&mut evictions_low_residence_duration_metric_threshold);
patch
.heatmap_period
.map(|v| humantime::parse_duration(&v))?
.apply(&mut heatmap_period);
patch.heatmap_period.apply(&mut heatmap_period);
patch.lazy_slru_download.apply(&mut lazy_slru_download);
patch
.timeline_get_throttle
@@ -690,13 +654,9 @@ impl TenantConfig {
patch
.image_creation_preempt_threshold
.apply(&mut image_creation_preempt_threshold);
patch
.lsn_lease_length
.map(|v| humantime::parse_duration(&v))?
.apply(&mut lsn_lease_length);
patch.lsn_lease_length.apply(&mut lsn_lease_length);
patch
.lsn_lease_length_for_ts
.map(|v| humantime::parse_duration(&v))?
.apply(&mut lsn_lease_length_for_ts);
patch.timeline_offloading.apply(&mut timeline_offloading);
patch
@@ -713,7 +673,7 @@ impl TenantConfig {
.gc_compaction_ratio_percent
.apply(&mut gc_compaction_ratio_percent);
Ok(Self {
Self {
checkpoint_distance,
checkpoint_timeout,
compaction_target_size,
@@ -749,7 +709,7 @@ impl TenantConfig {
gc_compaction_enabled,
gc_compaction_initial_threshold_kb,
gc_compaction_ratio_percent,
})
}
}
}
@@ -1120,7 +1080,8 @@ pub struct TenantInfo {
/// Opaque explanation if gc is being blocked.
///
/// Only looked up for the individual tenant detail, not the listing.
/// Only looked up for the individual tenant detail, not the listing. This is purely for
/// debugging, not included in openapi.
#[serde(skip_serializing_if = "Option::is_none")]
pub gc_blocking: Option<String>,
}
@@ -1175,26 +1136,7 @@ pub struct TimelineInfo {
pub ancestor_lsn: Option<Lsn>,
pub last_record_lsn: Lsn,
pub prev_record_lsn: Option<Lsn>,
/// Legacy field for compat with control plane. Synonym of `min_readable_lsn`.
/// TODO: remove once control plane no longer reads it.
pub latest_gc_cutoff_lsn: Lsn,
/// The LSN up to which GC has advanced: older data may still exist but it is not available for clients.
/// This LSN is not suitable for deciding where to create branches etc: use [`TimelineInfo::min_readable_lsn`] instead,
/// as it is easier to reason about.
#[serde(default)]
pub applied_gc_cutoff_lsn: Lsn,
/// The upper bound of data which is either already GC'ed, or elegible to be GC'ed at any time based on PITR interval.
/// This LSN represents the "end of history" for this timeline, and callers should use it to figure out the oldest
/// LSN at which it is legal to create a branch or ephemeral endpoint.
///
/// Note that holders of valid LSN leases may be able to create branches and read pages earlier
/// than this LSN, but new leases may not be taken out earlier than this LSN.
#[serde(default)]
pub min_readable_lsn: Lsn,
pub disk_consistent_lsn: Lsn,
/// The LSN that we have succesfully uploaded to remote storage
@@ -2281,9 +2223,8 @@ impl Default for PageTraceEvent {
#[cfg(test)]
mod tests {
use std::str::FromStr;
use serde_json::json;
use std::str::FromStr;
use super::*;
@@ -2544,7 +2485,7 @@ mod tests {
..base.clone()
};
let patched = base.apply_patch(decoded.config).unwrap();
let patched = base.apply_patch(decoded.config);
assert_eq!(patched, expected);
}

View File

@@ -1,7 +1,5 @@
use std::time::SystemTime;
use utils::serde_percent::Percent;
use utils::serde_system_time;
use utils::{serde_percent::Percent, serde_system_time};
/// Pageserver current utilization and scoring for how good candidate the pageserver would be for
/// the next tenant.
@@ -133,12 +131,12 @@ impl PageserverUtilization {
/// Test helper
pub mod test_utilization {
use std::time::SystemTime;
use utils::serde_percent::Percent;
use utils::serde_system_time::{self};
use super::PageserverUtilization;
use std::time::SystemTime;
use utils::{
serde_percent::Percent,
serde_system_time::{self},
};
// Parameters of the imaginary node used for test utilization instances
const TEST_DISK_SIZE: u64 = 1024 * 1024 * 1024 * 1024;

View File

@@ -1,7 +1,7 @@
//! This module defines the WAL record format used within the pageserver.
use bytes::Bytes;
use postgres_ffi::walrecord::{MultiXactMember, describe_postgres_wal_record};
use postgres_ffi::walrecord::{describe_postgres_wal_record, MultiXactMember};
use postgres_ffi::{MultiXactId, MultiXactOffset, TimestampTz, TransactionId};
use serde::{Deserialize, Serialize};
use utils::bin_ser::DeserializeError;

View File

@@ -1,10 +1,10 @@
use serde::{Deserialize, Serialize};
use std::cmp::Ordering;
use std::fmt;
use postgres_ffi::Oid;
use postgres_ffi::pg_constants::GLOBALTABLESPACE_OID;
use postgres_ffi::relfile_utils::{MAIN_FORKNUM, forkname_to_number, forknumber_to_name};
use serde::{Deserialize, Serialize};
use postgres_ffi::relfile_utils::{forkname_to_number, forknumber_to_name, MAIN_FORKNUM};
use postgres_ffi::Oid;
///
/// Relation data file segment id throughout the Postgres cluster.

View File

@@ -33,13 +33,12 @@
use std::hash::{Hash, Hasher};
#[doc(inline)]
pub use ::utils::shard::*;
use crate::{key::Key, models::ShardParameters};
use postgres_ffi::relfile_utils::INIT_FORKNUM;
use serde::{Deserialize, Serialize};
use crate::key::Key;
use crate::models::ShardParameters;
#[doc(inline)]
pub use ::utils::shard::*;
/// The ShardIdentity contains enough information to map a [`Key`] to a [`ShardNumber`],
/// and to check whether that [`ShardNumber`] is the same as the current shard.
@@ -338,8 +337,7 @@ pub fn describe(
mod tests {
use std::str::FromStr;
use utils::Hex;
use utils::id::TenantId;
use utils::{id::TenantId, Hex};
use super::*;

View File

@@ -6,9 +6,9 @@
use serde::{Deserialize, Serialize};
use utils::id::NodeId;
use crate::controller_api::NodeRegisterRequest;
use crate::models::LocationConfigMode;
use crate::shard::TenantShardId;
use crate::{
controller_api::NodeRegisterRequest, models::LocationConfigMode, shard::TenantShardId,
};
/// Upcall message sent by the pageserver to the configured `control_plane_api` on
/// startup.
@@ -30,7 +30,7 @@ fn default_mode() -> LocationConfigMode {
pub struct ReAttachResponseTenant {
pub id: TenantShardId,
/// Mandatory if LocationConfigMode is None or set to an Attached* mode
pub r#gen: Option<u32>,
pub gen: Option<u32>,
/// Default value only for backward compat: this field should be set
#[serde(default = "default_mode")]
@@ -44,7 +44,7 @@ pub struct ReAttachResponse {
#[derive(Serialize, Deserialize)]
pub struct ValidateRequestTenant {
pub id: TenantShardId,
pub r#gen: u32,
pub gen: u32,
}
#[derive(Serialize, Deserialize)]

View File

@@ -7,11 +7,10 @@
//! Note that the [`Value`] type is used for the permananent storage format, so any
//! changes to it must be backwards compatible.
use crate::record::NeonWalRecord;
use bytes::Bytes;
use serde::{Deserialize, Serialize};
use crate::record::NeonWalRecord;
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
pub enum Value {
/// An Image value contains a full copy of the value
@@ -84,11 +83,11 @@ impl ValueBytes {
#[cfg(test)]
mod test {
use super::*;
use bytes::Bytes;
use utils::bin_ser::BeSer;
use super::*;
macro_rules! roundtrip {
($orig:expr, $expected:expr) => {{
let orig: Value = $orig;

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